Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1659 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1198. Min Range: -9.1198
Max Act: 9.1198. Min Act: -0.1700
Data Index: 1176569 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1198. Min Range: -9.1198
Max Act: 9.0573. Min Act: -0.1700
Data Index: 7848279 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.9948. Min Act: -0.1700
Data Index: 8041810 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.9948. Min Act: -0.1700
Data Index: 1767165 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.9323. Min Act: -0.1700
Data Index: 6106531 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.9323. Min Act: -0.1700
Data Index: 6164339 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.8698. Min Act: -0.1700
Data Index: 6309546 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.8698. Min Act: -0.1700
Data Index: 4727287 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.8698. Min Act: -0.1700
Data Index: 4349739 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.8698. Min Act: -0.1700
Data Index: 2487464 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.8698. Min Act: -0.1700
Data Index: 3779173 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.8698. Min Act: -0.1700
Data Index: 7763929 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.8698. Min Act: -0.1700
Data Index: 6427803 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.7448. Min Act: -0.1700
Data Index: 2574751 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.7448. Min Act: -0.1700
Data Index: 4686018 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.7448. Min Act: -0.1700
Data Index: 1410628 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.7448. Min Act: -0.1700
Data Index: 2182059 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.6823. Min Act: -0.1700
Data Index: 6463510 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.6823. Min Act: -0.1700
Data Index: 4720340 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1198. Min Range: -9.1198
Max Act: 8.6198. Min Act: -0.1700
Data Index: 3553407 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19