< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1464 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.0314. Min Range: -2.0314

Max Act: 2.0314. Min Act: -0.1700

Data Index: 8675462 (Open Web Text)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0314. Min Range: -2.0314

Max Act: 2.0134. Min Act: -0.1700

Data Index: 8075018 (Open Web Text)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9939. Min Act: -0.1700

Data Index: 8743165 (Open Web Text)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9607. Min Act: -0.1700

Data Index: 322609 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9425. Min Act: -0.1700

Data Index: 2181749 (Open Web Text)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9408. Min Act: -0.1700

Data Index: 3164056 (Open Web Text)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9234. Min Act: -0.1700

Data Index: 3355266 (Open Web Text)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9306. Min Act: -0.1700

Data Index: 3680096 (Open Web Text)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9302. Min Act: -0.1700

Data Index: 8651239 (Open Web Text)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9083. Min Act: -0.1700

Data Index: 1040129 (Open Web Text)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9206. Min Act: -0.1700

Data Index: 8193583 (Open Web Text)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9417. Min Act: -0.1700

Data Index: 8512201 (Open Web Text)

Max Activating Token Index: 296

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9076. Min Act: -0.1700

Data Index: 524117 (Open Web Text)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9084. Min Act: -0.1700

Data Index: 6660353 (Open Web Text)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9084. Min Act: -0.1700

Data Index: 103735 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9023. Min Act: -0.1700

Data Index: 3458918 (Open Web Text)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9159. Min Act: -0.1700

Data Index: 8712019 (Open Web Text)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.8983. Min Act: -0.1700

Data Index: 2261972 (Open Web Text)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.9058. Min Act: -0.1700

Data Index: 8291433 (Open Web Text)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0314. Min Range: -2.0314

Max Act: 1.8903. Min Act: -0.1700

Data Index: 1188491 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #19