Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 4191 in Layer 46

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.8080. Min Act: -0.1700

Data Index: 7162542 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4330. Min Act: -0.1700

Data Index: 1423501 (Open Web Text)

Max Activating Token Index: 866

Text #2

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3393. Min Act: -0.1700

Data Index: 7044647 (Open Web Text)

Max Activating Token Index: 949

Text #3

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.2768. Min Act: -0.1700

Data Index: 6745174 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1518. Min Act: -0.1700

Data Index: 2014930 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1518. Min Act: -0.1700

Data Index: 966415 (Open Web Text)

Max Activating Token Index: 146

Text #6

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1518. Min Act: -0.1700

Data Index: 5464984 (Open Web Text)

Max Activating Token Index: 749

Text #7

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.0893. Min Act: -0.1700

Data Index: 4376480 (Open Web Text)

Max Activating Token Index: 610

Text #8

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.0893. Min Act: -0.1700

Data Index: 6134629 (Open Web Text)

Max Activating Token Index: 767

Text #9

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9955. Min Act: -0.1700

Data Index: 1343296 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9955. Min Act: -0.1700

Data Index: 6745176 (Open Web Text)

Max Activating Token Index: 933

Text #11

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9330. Min Act: -0.1700

Data Index: 3642715 (Open Web Text)

Max Activating Token Index: 336

Text #12

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9643. Min Act: -0.1700

Data Index: 4722459 (Open Web Text)

Max Activating Token Index: 733

Text #13

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9018. Min Act: -0.1700

Data Index: 6134631 (Open Web Text)

Max Activating Token Index: 629

Text #14

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9018. Min Act: -0.1700

Data Index: 3107686 (Open Web Text)

Max Activating Token Index: 650

Text #15

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9018. Min Act: -0.1700

Data Index: 706182 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.8705. Min Act: -0.1700

Data Index: 7096971 (Open Web Text)

Max Activating Token Index: 348

Text #17

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.8705. Min Act: -0.1700

Data Index: 8408252 (Open Web Text)

Max Activating Token Index: 379

Text #18

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.8393. Min Act: -0.1700

Data Index: 5416222 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.8080. Min Act: -0.1700

Data Index: 265041 (Open Web Text)

Max Activating Token Index: 626