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

Dataset: Open Web Text

Neuron 2925 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: 4.7938. Min Range: -4.7938

Max Act: 4.7938. Min Act: -0.1700

Data Index: 970649 (Open Web Text)

Max Activating Token Index: 41

Text #1

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.7868. Min Act: -0.1700

Data Index: 1125265 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.7227. Min Act: -0.1700

Data Index: 2564065 (Open Web Text)

Max Activating Token Index: 606

Text #3

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6787. Min Act: -0.1700

Data Index: 6197614 (Open Web Text)

Max Activating Token Index: 308

Text #4

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6829. Min Act: -0.1700

Data Index: 4016600 (Open Web Text)

Max Activating Token Index: 828

Text #5

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6785. Min Act: -0.1700

Data Index: 3296847 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6462. Min Act: -0.1700

Data Index: 8524499 (Open Web Text)

Max Activating Token Index: 289

Text #7

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6900. Min Act: -0.1700

Data Index: 152287 (Open Web Text)

Max Activating Token Index: 81

Text #8

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6374. Min Act: -0.1700

Data Index: 7839783 (Open Web Text)

Max Activating Token Index: 696

Text #9

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6229. Min Act: -0.1700

Data Index: 2825921 (Open Web Text)

Max Activating Token Index: 443

Text #10

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6087. Min Act: -0.1700

Data Index: 4485777 (Open Web Text)

Max Activating Token Index: 763

Text #11

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6079. Min Act: -0.1700

Data Index: 5256601 (Open Web Text)

Max Activating Token Index: 518

Text #12

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.6116. Min Act: -0.1700

Data Index: 3679533 (Open Web Text)

Max Activating Token Index: 861

Text #13

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.5713. Min Act: -0.1700

Data Index: 8113142 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.5859. Min Act: -0.1700

Data Index: 3447841 (Open Web Text)

Max Activating Token Index: 610

Text #15

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.5518. Min Act: -0.1700

Data Index: 5747564 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.5311. Min Act: -0.1700

Data Index: 580095 (Open Web Text)

Max Activating Token Index: 127

Text #17

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.5135. Min Act: -0.1700

Data Index: 3321982 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.5058. Min Act: -0.1700

Data Index: 3044778 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 4.7938. Min Range: -4.7938

Max Act: 4.4898. Min Act: -0.1700

Data Index: 1512547 (Open Web Text)

Max Activating Token Index: 242