Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5826 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0941. Min Range: -6.0941
Max Act: 6.0941. Min Act: -0.1700
Data Index: 5538803 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0941. Min Range: -6.0941
Max Act: 6.0316. Min Act: -0.1700
Data Index: 3530573 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0941. Min Range: -6.0941
Max Act: 6.0004. Min Act: -0.1700
Data Index: 8781341 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0941. Min Range: -6.0941
Max Act: 6.0004. Min Act: -0.1700
Data Index: 3965810 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.9691. Min Act: -0.1700
Data Index: 471187 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.9691. Min Act: -0.1700
Data Index: 7692132 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.9379. Min Act: -0.1700
Data Index: 5029161 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.9379. Min Act: -0.1700
Data Index: 948780 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.8754. Min Act: -0.1700
Data Index: 6859059 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.9066. Min Act: -0.1700
Data Index: 7650330 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.9066. Min Act: -0.1700
Data Index: 7374048 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.9066. Min Act: -0.1700
Data Index: 6892249 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.9066. Min Act: -0.1700
Data Index: 1827241 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.8754. Min Act: -0.1700
Data Index: 2181629 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.8754. Min Act: -0.1700
Data Index: 5692518 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.9066. Min Act: -0.1700
Data Index: 7855939 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.8441. Min Act: -0.1700
Data Index: 6753330 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.8754. Min Act: -0.1700
Data Index: 3694329 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.8754. Min Act: -0.1700
Data Index: 4912360 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0941. Min Range: -6.0941
Max Act: 5.8441. Min Act: -0.1700
Data Index: 2488290 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19