Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3816. Min Range: -6.3816
Max Act: 6.3816. Min Act: -0.1700
Data Index: 5172224 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3816. Min Range: -6.3816
Max Act: 6.1941. Min Act: -0.1700
Data Index: 6985044 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3816. Min Range: -6.3816
Max Act: 6.1629. Min Act: -0.1700
Data Index: 3474113 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3816. Min Range: -6.3816
Max Act: 6.1316. Min Act: -0.1700
Data Index: 572362 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3816. Min Range: -6.3816
Max Act: 6.1004. Min Act: -0.1700
Data Index: 5758480 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3816. Min Range: -6.3816
Max Act: 6.0691. Min Act: -0.1700
Data Index: 2297161 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3816. Min Range: -6.3816
Max Act: 6.0691. Min Act: -0.1700
Data Index: 7076365 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3816. Min Range: -6.3816
Max Act: 6.0691. Min Act: -0.1700
Data Index: 3283461 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3816. Min Range: -6.3816
Max Act: 6.0066. Min Act: -0.1700
Data Index: 8420273 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.9129. Min Act: -0.1700
Data Index: 3051662 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.8504. Min Act: -0.1700
Data Index: 4633900 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.8191. Min Act: -0.1700
Data Index: 1667574 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.7879. Min Act: -0.1700
Data Index: 1114708 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.7879. Min Act: -0.1700
Data Index: 4125845 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.7566. Min Act: -0.1700
Data Index: 1546375 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.7566. Min Act: -0.1700
Data Index: 3664470 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.7566. Min Act: -0.1700
Data Index: 3447630 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.7566. Min Act: -0.1700
Data Index: 4509379 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.7566. Min Act: -0.1700
Data Index: 4418466 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3816. Min Range: -6.3816
Max Act: 5.7566. Min Act: -0.1700
Data Index: 3701986 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19