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

Dataset: Open Web Text

Neuron 1227 in Layer 2

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: 5.6833. Min Range: -5.6833

Max Act: 5.6833. Min Act: -0.1700

Data Index: 7275808 (Open Web Text)

Max Activating Token Index: 259

Text #1

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5254. Min Act: -0.1700

Data Index: 668299 (Open Web Text)

Max Activating Token Index: 448

Text #2

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5515. Min Act: -0.1700

Data Index: 3532666 (Open Web Text)

Max Activating Token Index: 310

Text #3

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5246. Min Act: -0.1700

Data Index: 5588581 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5498. Min Act: -0.1700

Data Index: 1746576 (Open Web Text)

Max Activating Token Index: 126

Text #5

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5191. Min Act: -0.1700

Data Index: 5769071 (Open Web Text)

Max Activating Token Index: 720

Text #6

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5141. Min Act: -0.1700

Data Index: 7642669 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5340. Min Act: -0.1700

Data Index: 627861 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4818. Min Act: -0.1700

Data Index: 6312282 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4959. Min Act: -0.1700

Data Index: 5684252 (Open Web Text)

Max Activating Token Index: 232

Text #10

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4933. Min Act: -0.1700

Data Index: 8542277 (Open Web Text)

Max Activating Token Index: 929

Text #11

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4169. Min Act: -0.1700

Data Index: 2780904 (Open Web Text)

Max Activating Token Index: 367

Text #12

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4677. Min Act: -0.1700

Data Index: 5660005 (Open Web Text)

Max Activating Token Index: 320

Text #13

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4507. Min Act: -0.1700

Data Index: 1030288 (Open Web Text)

Max Activating Token Index: 523

Text #14

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4764. Min Act: -0.1700

Data Index: 5159346 (Open Web Text)

Max Activating Token Index: 317

Text #15

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4144. Min Act: -0.1700

Data Index: 4870573 (Open Web Text)

Max Activating Token Index: 204

Text #16

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.3818. Min Act: -0.1700

Data Index: 5264414 (Open Web Text)

Max Activating Token Index: 887

Text #17

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4173. Min Act: -0.1700

Data Index: 347515 (Open Web Text)

Max Activating Token Index: 79

Text #18

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4300. Min Act: -0.1700

Data Index: 4542166 (Open Web Text)

Max Activating Token Index: 367

Text #19

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.3904. Min Act: -0.1700

Data Index: 2001295 (Open Web Text)

Max Activating Token Index: 103