Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9346. Min Range: -7.9346
Max Act: 7.9346. Min Act: -0.1700
Data Index: 5125903 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9346. Min Range: -7.9346
Max Act: 7.3721. Min Act: -0.1700
Data Index: 2114066 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9346. Min Range: -7.9346
Max Act: 7.3409. Min Act: -0.1700
Data Index: 7222464 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9346. Min Range: -7.9346
Max Act: 7.2471. Min Act: -0.1700
Data Index: 4064075 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9346. Min Range: -7.9346
Max Act: 7.0909. Min Act: -0.1700
Data Index: 3981836 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9346. Min Range: -7.9346
Max Act: 7.0284. Min Act: -0.1700
Data Index: 5820823 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9971. Min Act: -0.1700
Data Index: 2296590 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9971. Min Act: -0.1700
Data Index: 8106834 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9971. Min Act: -0.1700
Data Index: 6772937 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9659. Min Act: -0.1700
Data Index: 5820819 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9346. Min Act: -0.1700
Data Index: 3864132 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9346. Min Act: -0.1700
Data Index: 1883371 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9346. Min Act: -0.1700
Data Index: 2163279 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9659. Min Act: -0.1700
Data Index: 7430960 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9659. Min Act: -0.1700
Data Index: 2199662 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.9034. Min Act: -0.1700
Data Index: 1237552 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.8096. Min Act: -0.1700
Data Index: 1990913 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.8721. Min Act: -0.1700
Data Index: 7452754 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.7784. Min Act: -0.1700
Data Index: 5803747 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9346. Min Range: -7.9346
Max Act: 6.7784. Min Act: -0.1700
Data Index: 1770939 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19