Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0399. Min Range: -7.0399
Max Act: 7.0399. Min Act: -0.1700
Data Index: 4328970 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.8211. Min Act: -0.1700
Data Index: 3141951 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.7899. Min Act: -0.1700
Data Index: 926719 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.7274. Min Act: -0.1700
Data Index: 7243630 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6961. Min Act: -0.1700
Data Index: 5678143 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6961. Min Act: -0.1700
Data Index: 3969620 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6961. Min Act: -0.1700
Data Index: 8184774 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6961. Min Act: -0.1700
Data Index: 6758229 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6336. Min Act: -0.1700
Data Index: 4884168 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6336. Min Act: -0.1700
Data Index: 4117697 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6024. Min Act: -0.1700
Data Index: 2616228 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6024. Min Act: -0.1700
Data Index: 3756780 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6024. Min Act: -0.1700
Data Index: 2139777 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5399. Min Act: -0.1700
Data Index: 1577885 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5399. Min Act: -0.1700
Data Index: 3124293 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5711. Min Act: -0.1700
Data Index: 810736 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4774. Min Act: -0.1700
Data Index: 1059447 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5399. Min Act: -0.1700
Data Index: 7580917 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5399. Min Act: -0.1700
Data Index: 2762083 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5086. Min Act: -0.1700
Data Index: 4974279 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19