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

Dataset: Open Web Text

Neuron 1066 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: 3.4279. Min Range: -3.4279

Max Act: 3.4212. Min Act: -0.1700

Data Index: 905683 (Open Web Text)

Max Activating Token Index: 223

Text #1

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.4279. Min Act: -0.1700

Data Index: 1303585 (Open Web Text)

Max Activating Token Index: 267

Text #2

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.4142. Min Act: -0.1700

Data Index: 3855112 (Open Web Text)

Max Activating Token Index: 741

Text #3

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3687. Min Act: -0.1700

Data Index: 7971381 (Open Web Text)

Max Activating Token Index: 551

Text #4

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3415. Min Act: -0.1700

Data Index: 7288740 (Open Web Text)

Max Activating Token Index: 714

Text #5

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3567. Min Act: -0.1700

Data Index: 7794434 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3557. Min Act: -0.1700

Data Index: 2349082 (Open Web Text)

Max Activating Token Index: 531

Text #7

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3604. Min Act: -0.1700

Data Index: 4579816 (Open Web Text)

Max Activating Token Index: 802

Text #8

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3380. Min Act: -0.1700

Data Index: 3628462 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3216. Min Act: -0.1700

Data Index: 8111138 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3311. Min Act: -0.1700

Data Index: 1509935 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3173. Min Act: -0.1700

Data Index: 4926058 (Open Web Text)

Max Activating Token Index: 221

Text #12

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3079. Min Act: -0.1700

Data Index: 4668240 (Open Web Text)

Max Activating Token Index: 649

Text #13

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3341. Min Act: -0.1700

Data Index: 5628862 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3245. Min Act: -0.1700

Data Index: 7254269 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3295. Min Act: -0.1700

Data Index: 6909315 (Open Web Text)

Max Activating Token Index: 495

Text #16

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3128. Min Act: -0.1700

Data Index: 7876228 (Open Web Text)

Max Activating Token Index: 929

Text #17

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.3171. Min Act: -0.1700

Data Index: 2151217 (Open Web Text)

Max Activating Token Index: 912

Text #18

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.2994. Min Act: -0.1700

Data Index: 7547184 (Open Web Text)

Max Activating Token Index: 77

Text #19

Max Range: 3.4279. Min Range: -3.4279

Max Act: 3.2927. Min Act: -0.1700

Data Index: 2196778 (Open Web Text)

Max Activating Token Index: 622