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

Dataset: Open Web Text

Neuron 2803 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: 3.7294. Min Range: -3.7294

Max Act: 3.7294. Min Act: -0.1700

Data Index: 2261590 (Open Web Text)

Max Activating Token Index: 798

Text #1

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.6909. Min Act: -0.1700

Data Index: 6867817 (Open Web Text)

Max Activating Token Index: 583

Text #2

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.6698. Min Act: -0.1700

Data Index: 368859 (Open Web Text)

Max Activating Token Index: 397

Text #3

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.6303. Min Act: -0.1700

Data Index: 271832 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.6341. Min Act: -0.1700

Data Index: 170206 (Open Web Text)

Max Activating Token Index: 955

Text #5

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.5776. Min Act: -0.1700

Data Index: 2006433 (Open Web Text)

Max Activating Token Index: 699

Text #6

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.5594. Min Act: -0.1700

Data Index: 6556476 (Open Web Text)

Max Activating Token Index: 977

Text #7

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.5500. Min Act: -0.1700

Data Index: 523489 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.5296. Min Act: -0.1700

Data Index: 7231539 (Open Web Text)

Max Activating Token Index: 321

Text #9

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.5183. Min Act: -0.1700

Data Index: 1715947 (Open Web Text)

Max Activating Token Index: 232

Text #10

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.5343. Min Act: -0.1700

Data Index: 8555396 (Open Web Text)

Max Activating Token Index: 180

Text #11

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.5207. Min Act: -0.1700

Data Index: 7325195 (Open Web Text)

Max Activating Token Index: 659

Text #12

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.4770. Min Act: -0.1700

Data Index: 1620896 (Open Web Text)

Max Activating Token Index: 731

Text #13

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.4859. Min Act: -0.1700

Data Index: 3133104 (Open Web Text)

Max Activating Token Index: 198

Text #14

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.5223. Min Act: -0.1700

Data Index: 1510513 (Open Web Text)

Max Activating Token Index: 753

Text #15

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.4726. Min Act: -0.1700

Data Index: 2651141 (Open Web Text)

Max Activating Token Index: 521

Text #16

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.5157. Min Act: -0.1700

Data Index: 7231544 (Open Web Text)

Max Activating Token Index: 359

Text #17

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.4843. Min Act: -0.1700

Data Index: 6323426 (Open Web Text)

Max Activating Token Index: 343

Text #18

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.4983. Min Act: -0.1700

Data Index: 7486661 (Open Web Text)

Max Activating Token Index: 666

Text #19

Max Range: 3.7294. Min Range: -3.7294

Max Act: 3.4784. Min Act: -0.1700

Data Index: 988824 (Open Web Text)

Max Activating Token Index: 143