Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0083. Min Range: -6.0083
Max Act: 6.0083. Min Act: -0.1700
Data Index: 3729033 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.7583. Min Act: -0.1700
Data Index: 1181500 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6958. Min Act: -0.1700
Data Index: 6323718 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6645. Min Act: -0.1700
Data Index: 7621729 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6958. Min Act: -0.1700
Data Index: 2324649 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6333. Min Act: -0.1700
Data Index: 8462078 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6020. Min Act: -0.1700
Data Index: 1797300 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6645. Min Act: -0.1700
Data Index: 5501076 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6333. Min Act: -0.1700
Data Index: 2515912 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6333. Min Act: -0.1700
Data Index: 7039338 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6333. Min Act: -0.1700
Data Index: 2057444 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.5708. Min Act: -0.1700
Data Index: 6745171 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.5708. Min Act: -0.1700
Data Index: 1785554 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.5708. Min Act: -0.1700
Data Index: 3497216 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.5708. Min Act: -0.1700
Data Index: 6912972 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.6020. Min Act: -0.1700
Data Index: 4846745 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.5395. Min Act: -0.1700
Data Index: 7120817 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.5395. Min Act: -0.1700
Data Index: 2087231 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.5395. Min Act: -0.1700
Data Index: 974941 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0083. Min Range: -6.0083
Max Act: 5.5395. Min Act: -0.1700
Data Index: 5525009 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19