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

Dataset: Open Web Text

Neuron 853 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: 3.5260. Min Range: -3.5260

Max Act: 3.5199. Min Act: -0.1700

Data Index: 6105087 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.5260. Min Act: -0.1700

Data Index: 4248317 (Open Web Text)

Max Activating Token Index: 519

Text #2

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.4041. Min Act: -0.1699

Data Index: 1562876 (Open Web Text)

Max Activating Token Index: 205

Text #3

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3916. Min Act: -0.1700

Data Index: 2042167 (Open Web Text)

Max Activating Token Index: 217

Text #4

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3866. Min Act: -0.1700

Data Index: 2146022 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3935. Min Act: -0.1700

Data Index: 7501576 (Open Web Text)

Max Activating Token Index: 794

Text #6

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3720. Min Act: -0.1700

Data Index: 309548 (Open Web Text)

Max Activating Token Index: 516

Text #7

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3870. Min Act: -0.1700

Data Index: 5074308 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3745. Min Act: -0.1700

Data Index: 7111863 (Open Web Text)

Max Activating Token Index: 763

Text #9

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3666. Min Act: -0.1700

Data Index: 6346676 (Open Web Text)

Max Activating Token Index: 553

Text #10

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3538. Min Act: -0.1700

Data Index: 306241 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3372. Min Act: -0.1700

Data Index: 3477760 (Open Web Text)

Max Activating Token Index: 954

Text #12

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3421. Min Act: -0.1700

Data Index: 7825198 (Open Web Text)

Max Activating Token Index: 868

Text #13

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3522. Min Act: -0.1700

Data Index: 4248321 (Open Web Text)

Max Activating Token Index: 212

Text #14

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3524. Min Act: -0.1700

Data Index: 6504877 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3409. Min Act: -0.1700

Data Index: 7078288 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3039. Min Act: -0.1700

Data Index: 4805391 (Open Web Text)

Max Activating Token Index: 208

Text #17

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3284. Min Act: -0.1700

Data Index: 5929407 (Open Web Text)

Max Activating Token Index: 745

Text #18

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3103. Min Act: -0.1700

Data Index: 7078296 (Open Web Text)

Max Activating Token Index: 506

Text #19

Max Range: 3.5260. Min Range: -3.5260

Max Act: 3.3091. Min Act: -0.1700

Data Index: 7078301 (Open Web Text)

Max Activating Token Index: 199