< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2559 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: 2.8240. Min Range: -2.8240

Max Act: 2.8240. Min Act: -0.1700

Data Index: 173108 (Open Web Text)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.7776. Min Act: -0.1700

Data Index: 7619075 (Open Web Text)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.7292. Min Act: -0.1700

Data Index: 1044421 (Open Web Text)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.7538. Min Act: -0.1700

Data Index: 2554364 (Open Web Text)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.7297. Min Act: -0.1700

Data Index: 3794838 (Open Web Text)

Max Activating Token Index: 731

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6832. Min Act: -0.1700

Data Index: 7358375 (Open Web Text)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6646. Min Act: -0.1700

Data Index: 7692907 (Open Web Text)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6466. Min Act: -0.1700

Data Index: 1513653 (Open Web Text)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6484. Min Act: -0.1700

Data Index: 1965285 (Open Web Text)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6129. Min Act: -0.1700

Data Index: 2224200 (Open Web Text)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6283. Min Act: -0.1700

Data Index: 144418 (Open Web Text)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6569. Min Act: -0.1700

Data Index: 5903857 (Open Web Text)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6073. Min Act: -0.1700

Data Index: 3395210 (Open Web Text)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6128. Min Act: -0.1700

Data Index: 7823432 (Open Web Text)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6127. Min Act: -0.1700

Data Index: 6808167 (Open Web Text)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6062. Min Act: -0.1700

Data Index: 576191 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6299. Min Act: -0.1700

Data Index: 6457977 (Open Web Text)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6164. Min Act: -0.1700

Data Index: 930200 (Open Web Text)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6414. Min Act: -0.1700

Data Index: 6038585 (Open Web Text)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8240. Min Range: -2.8240

Max Act: 2.6266. Min Act: -0.1700

Data Index: 1461190 (Open Web Text)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #19