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

Dataset: Open Web Text

Neuron 1911 in Layer 3

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: 3.7949. Min Range: -3.7949

Max Act: 3.7949. Min Act: -0.1700

Data Index: 7786899 (Open Web Text)

Max Activating Token Index: 669

Text #1

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.6465. Min Act: -0.1700

Data Index: 3373903 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.6529. Min Act: -0.1700

Data Index: 7569909 (Open Web Text)

Max Activating Token Index: 182

Text #3

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.6408. Min Act: -0.1700

Data Index: 6010921 (Open Web Text)

Max Activating Token Index: 823

Text #4

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.6320. Min Act: -0.1700

Data Index: 4893403 (Open Web Text)

Max Activating Token Index: 274

Text #5

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.6096. Min Act: -0.1700

Data Index: 7811749 (Open Web Text)

Max Activating Token Index: 296

Text #6

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5915. Min Act: -0.1700

Data Index: 4747772 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5830. Min Act: -0.1700

Data Index: 2028574 (Open Web Text)

Max Activating Token Index: 55

Text #8

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5716. Min Act: -0.1700

Data Index: 4569152 (Open Web Text)

Max Activating Token Index: 725

Text #9

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5583. Min Act: -0.1700

Data Index: 163495 (Open Web Text)

Max Activating Token Index: 177

Text #10

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5564. Min Act: -0.1700

Data Index: 3373902 (Open Web Text)

Max Activating Token Index: 448

Text #11

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5853. Min Act: -0.1700

Data Index: 7616552 (Open Web Text)

Max Activating Token Index: 197

Text #12

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.6090. Min Act: -0.1700

Data Index: 3615692 (Open Web Text)

Max Activating Token Index: 615

Text #13

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5337. Min Act: -0.1700

Data Index: 1928460 (Open Web Text)

Max Activating Token Index: 396

Text #14

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5679. Min Act: -0.1700

Data Index: 2081437 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5703. Min Act: -0.1700

Data Index: 8087955 (Open Web Text)

Max Activating Token Index: 610

Text #16

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5537. Min Act: -0.1700

Data Index: 2266495 (Open Web Text)

Max Activating Token Index: 791

Text #17

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5539. Min Act: -0.1700

Data Index: 7691221 (Open Web Text)

Max Activating Token Index: 711

Text #18

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5185. Min Act: -0.1700

Data Index: 3947655 (Open Web Text)

Max Activating Token Index: 80

Text #19

Max Range: 3.7949. Min Range: -3.7949

Max Act: 3.5114. Min Act: -0.1700

Data Index: 6708018 (Open Web Text)

Max Activating Token Index: 504