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

Dataset: Open Web Text

Neuron 79 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: 3.6574. Min Range: -3.6574

Max Act: 3.6574. Min Act: -0.1700

Data Index: 5507006 (Open Web Text)

Max Activating Token Index: 414

Text #1

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.6209. Min Act: -0.1700

Data Index: 3086697 (Open Web Text)

Max Activating Token Index: 629

Text #2

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.6015. Min Act: -0.1700

Data Index: 1334983 (Open Web Text)

Max Activating Token Index: 570

Text #3

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.5918. Min Act: -0.1700

Data Index: 6583371 (Open Web Text)

Max Activating Token Index: 991

Text #4

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.5586. Min Act: -0.1700

Data Index: 1498662 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.5498. Min Act: -0.1700

Data Index: 4509581 (Open Web Text)

Max Activating Token Index: 301

Text #6

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.5332. Min Act: -0.1700

Data Index: 2921714 (Open Web Text)

Max Activating Token Index: 649

Text #7

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.5116. Min Act: -0.1700

Data Index: 1095681 (Open Web Text)

Max Activating Token Index: 326

Text #8

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4890. Min Act: -0.1700

Data Index: 5604554 (Open Web Text)

Max Activating Token Index: 277

Text #9

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4699. Min Act: -0.1700

Data Index: 7738966 (Open Web Text)

Max Activating Token Index: 675

Text #10

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4652. Min Act: -0.1700

Data Index: 5090880 (Open Web Text)

Max Activating Token Index: 145

Text #11

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4649. Min Act: -0.1700

Data Index: 7478370 (Open Web Text)

Max Activating Token Index: 340

Text #12

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4477. Min Act: -0.1700

Data Index: 7961438 (Open Web Text)

Max Activating Token Index: 875

Text #13

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4360. Min Act: -0.1700

Data Index: 2041231 (Open Web Text)

Max Activating Token Index: 955

Text #14

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4475. Min Act: -0.1700

Data Index: 2995617 (Open Web Text)

Max Activating Token Index: 262

Text #15

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4358. Min Act: -0.1700

Data Index: 6581065 (Open Web Text)

Max Activating Token Index: 146

Text #16

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4288. Min Act: -0.1700

Data Index: 7674204 (Open Web Text)

Max Activating Token Index: 710

Text #17

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4256. Min Act: -0.1700

Data Index: 7028876 (Open Web Text)

Max Activating Token Index: 737

Text #18

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4271. Min Act: -0.1700

Data Index: 1019986 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.4300. Min Act: -0.1700

Data Index: 6886454 (Open Web Text)

Max Activating Token Index: 485