Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3787. Min Range: -6.3787
Max Act: 6.3787. Min Act: -0.1700
Data Index: 361600 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3787. Min Range: -6.3787
Max Act: 6.2537. Min Act: -0.1700
Data Index: 7398120 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3787. Min Range: -6.3787
Max Act: 6.2224. Min Act: -0.1700
Data Index: 4804054 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3787. Min Range: -6.3787
Max Act: 6.1287. Min Act: -0.1700
Data Index: 5246888 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3787. Min Range: -6.3787
Max Act: 6.0349. Min Act: -0.1700
Data Index: 6621160 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3787. Min Range: -6.3787
Max Act: 6.0037. Min Act: -0.1700
Data Index: 7449387 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.9724. Min Act: -0.1700
Data Index: 2024118 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.9724. Min Act: -0.1700
Data Index: 568986 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.9412. Min Act: -0.1700
Data Index: 381536 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.9099. Min Act: -0.1700
Data Index: 5395519 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.8787. Min Act: -0.1700
Data Index: 4136553 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.8787. Min Act: -0.1700
Data Index: 8413430 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.8474. Min Act: -0.1700
Data Index: 6335650 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.8162. Min Act: -0.1700
Data Index: 1573852 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.8162. Min Act: -0.1700
Data Index: 1833589 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.8162. Min Act: -0.1700
Data Index: 3502255 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.8162. Min Act: -0.1700
Data Index: 8292745 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.7849. Min Act: -0.1700
Data Index: 1731657 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.7849. Min Act: -0.1700
Data Index: 3506996 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3787. Min Range: -6.3787
Max Act: 5.7537. Min Act: -0.1700
Data Index: 8004008 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19