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

Dataset: Open Web Text

Neuron 845 in Layer 6

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: 4.6278. Min Range: -4.6278

Max Act: 4.6278. Min Act: -0.1700

Data Index: 3845499 (Open Web Text)

Max Activating Token Index: 995

Text #1

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.4965. Min Act: -0.1700

Data Index: 3066158 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.4125. Min Act: -0.1700

Data Index: 838488 (Open Web Text)

Max Activating Token Index: 428

Text #3

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3856. Min Act: -0.1700

Data Index: 3375023 (Open Web Text)

Max Activating Token Index: 830

Text #4

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3224. Min Act: -0.1700

Data Index: 5699888 (Open Web Text)

Max Activating Token Index: 866

Text #5

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3489. Min Act: -0.1700

Data Index: 7194874 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3201. Min Act: -0.1700

Data Index: 5193860 (Open Web Text)

Max Activating Token Index: 381

Text #7

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3144. Min Act: -0.1700

Data Index: 237878 (Open Web Text)

Max Activating Token Index: 477

Text #8

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3153. Min Act: -0.1700

Data Index: 2371788 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3120. Min Act: -0.1700

Data Index: 550980 (Open Web Text)

Max Activating Token Index: 406

Text #10

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3259. Min Act: -0.1700

Data Index: 241564 (Open Web Text)

Max Activating Token Index: 953

Text #11

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3055. Min Act: -0.1700

Data Index: 4810476 (Open Web Text)

Max Activating Token Index: 400

Text #12

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2903. Min Act: -0.1700

Data Index: 3686264 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2615. Min Act: -0.1700

Data Index: 842331 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2820. Min Act: -0.1700

Data Index: 1034196 (Open Web Text)

Max Activating Token Index: 932

Text #15

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3156. Min Act: -0.1700

Data Index: 7216680 (Open Web Text)

Max Activating Token Index: 562

Text #16

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2835. Min Act: -0.1700

Data Index: 6913570 (Open Web Text)

Max Activating Token Index: 317

Text #17

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2805. Min Act: -0.1700

Data Index: 6652697 (Open Web Text)

Max Activating Token Index: 889

Text #18

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2770. Min Act: -0.1700

Data Index: 5255508 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2312. Min Act: -0.1700

Data Index: 807640 (Open Web Text)

Max Activating Token Index: 54