< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 291 in Layer 4

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: 2.1232. Min Range: -2.1232

Max Act: 2.1232. Min Act: -0.1700

Data Index: 6112470 (Open Web Text)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1232. Min Range: -2.1232

Max Act: 2.0941. Min Act: -0.1700

Data Index: 6186166 (Open Web Text)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1232. Min Range: -2.1232

Max Act: 2.0469. Min Act: -0.1700

Data Index: 6112451 (Open Web Text)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1232. Min Range: -2.1232

Max Act: 2.0256. Min Act: -0.1700

Data Index: 8095025 (Open Web Text)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1232. Min Range: -2.1232

Max Act: 2.0258. Min Act: -0.1700

Data Index: 8388754 (Open Web Text)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1232. Min Range: -2.1232

Max Act: 2.0061. Min Act: -0.1700

Data Index: 6112475 (Open Web Text)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9883. Min Act: -0.1700

Data Index: 6112453 (Open Web Text)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9791. Min Act: -0.1700

Data Index: 3641372 (Open Web Text)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9854. Min Act: -0.1700

Data Index: 2169489 (Open Web Text)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9924. Min Act: -0.1700

Data Index: 6112473 (Open Web Text)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9607. Min Act: -0.1700

Data Index: 6112472 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9729. Min Act: -0.1700

Data Index: 6112456 (Open Web Text)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9567. Min Act: -0.1700

Data Index: 1021732 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9517. Min Act: -0.1700

Data Index: 6112454 (Open Web Text)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9436. Min Act: -0.1699

Data Index: 851241 (Open Web Text)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9522. Min Act: -0.1700

Data Index: 6112469 (Open Web Text)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9368. Min Act: -0.1700

Data Index: 6112450 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9431. Min Act: -0.1700

Data Index: 7249490 (Open Web Text)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9184. Min Act: -0.1700

Data Index: 6008465 (Open Web Text)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1232. Min Range: -2.1232

Max Act: 1.9302. Min Act: -0.1700

Data Index: 6186146 (Open Web Text)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #19