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

Dataset: Open Web Text

Neuron 837 in Layer 4

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: 3.7903. Min Range: -3.7903

Max Act: 3.7584. Min Act: -0.1700

Data Index: 5490886 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7611. Min Act: -0.1700

Data Index: 8205315 (Open Web Text)

Max Activating Token Index: 967

Text #2

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7882. Min Act: -0.1700

Data Index: 6553124 (Open Web Text)

Max Activating Token Index: 827

Text #3

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7636. Min Act: -0.1700

Data Index: 5978097 (Open Web Text)

Max Activating Token Index: 255

Text #4

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7903. Min Act: -0.1700

Data Index: 6500109 (Open Web Text)

Max Activating Token Index: 544

Text #5

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7456. Min Act: -0.1700

Data Index: 5593638 (Open Web Text)

Max Activating Token Index: 298

Text #6

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7521. Min Act: -0.1700

Data Index: 2695641 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7247. Min Act: -0.1700

Data Index: 3945868 (Open Web Text)

Max Activating Token Index: 772

Text #8

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7282. Min Act: -0.1700

Data Index: 5323995 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7439. Min Act: -0.1700

Data Index: 1947754 (Open Web Text)

Max Activating Token Index: 483

Text #10

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7593. Min Act: -0.1700

Data Index: 2141049 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7173. Min Act: -0.1700

Data Index: 7760610 (Open Web Text)

Max Activating Token Index: 53

Text #12

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7273. Min Act: -0.1700

Data Index: 267685 (Open Web Text)

Max Activating Token Index: 541

Text #13

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7063. Min Act: -0.1700

Data Index: 7349977 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7038. Min Act: -0.1700

Data Index: 6502506 (Open Web Text)

Max Activating Token Index: 955

Text #15

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.6921. Min Act: -0.1700

Data Index: 3185729 (Open Web Text)

Max Activating Token Index: 277

Text #16

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7028. Min Act: -0.1700

Data Index: 3069796 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.7027. Min Act: -0.1700

Data Index: 6263705 (Open Web Text)

Max Activating Token Index: 950

Text #18

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.6991. Min Act: -0.1700

Data Index: 7934753 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 3.7903. Min Range: -3.7903

Max Act: 3.6951. Min Act: -0.1700

Data Index: 2534460 (Open Web Text)

Max Activating Token Index: 364