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

Dataset: Open Web Text

Neuron 1748 in Layer 1

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: 5.8077. Min Range: -5.8077

Max Act: 5.8077. Min Act: -0.1700

Data Index: 5995177 (Open Web Text)

Max Activating Token Index: 817

Text #1

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7606. Min Act: -0.1700

Data Index: 7408998 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7981. Min Act: -0.1700

Data Index: 7278324 (Open Web Text)

Max Activating Token Index: 458

Text #3

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7513. Min Act: -0.1700

Data Index: 4383316 (Open Web Text)

Max Activating Token Index: 840

Text #4

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7208. Min Act: -0.1700

Data Index: 8321427 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7221. Min Act: -0.1700

Data Index: 304035 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7171. Min Act: -0.1700

Data Index: 3228305 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7264. Min Act: -0.1700

Data Index: 2125849 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6851. Min Act: -0.1700

Data Index: 5788551 (Open Web Text)

Max Activating Token Index: 270

Text #9

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7237. Min Act: -0.1700

Data Index: 6166495 (Open Web Text)

Max Activating Token Index: 655

Text #10

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7124. Min Act: -0.1700

Data Index: 8582243 (Open Web Text)

Max Activating Token Index: 570

Text #11

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7036. Min Act: -0.1700

Data Index: 4501416 (Open Web Text)

Max Activating Token Index: 613

Text #12

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7070. Min Act: -0.1700

Data Index: 4753730 (Open Web Text)

Max Activating Token Index: 313

Text #13

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7108. Min Act: -0.1700

Data Index: 6743538 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.7001. Min Act: -0.1700

Data Index: 8350225 (Open Web Text)

Max Activating Token Index: 282

Text #15

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6799. Min Act: -0.1700

Data Index: 380972 (Open Web Text)

Max Activating Token Index: 238

Text #16

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6690. Min Act: -0.1700

Data Index: 5773224 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6783. Min Act: -0.1700

Data Index: 6007942 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6733. Min Act: -0.1700

Data Index: 7169249 (Open Web Text)

Max Activating Token Index: 403

Text #19

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6782. Min Act: -0.1700

Data Index: 1501806 (Open Web Text)

Max Activating Token Index: 383