Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.9313. Min Act: -0.1700
Data Index: 8797096 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.7125. Min Act: -0.1700
Data Index: 7960743 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.6500. Min Act: -0.1700
Data Index: 3439746 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.5250. Min Act: -0.1700
Data Index: 2000525 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.5563. Min Act: -0.1700
Data Index: 2718884 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.5250. Min Act: -0.1700
Data Index: 1731615 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.5250. Min Act: -0.1700
Data Index: 5705555 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4938. Min Act: -0.1700
Data Index: 6284268 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4938. Min Act: -0.1700
Data Index: 6574327 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.5250. Min Act: -0.1700
Data Index: 2673127 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4625. Min Act: -0.1700
Data Index: 481233 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4938. Min Act: -0.1700
Data Index: 5304078 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4625. Min Act: -0.1700
Data Index: 4465889 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4313. Min Act: -0.1700
Data Index: 2543746 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4000. Min Act: -0.1700
Data Index: 6829348 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4000. Min Act: -0.1700
Data Index: 7623955 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4000. Min Act: -0.1700
Data Index: 2399236 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4000. Min Act: -0.1700
Data Index: 4724043 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.3688. Min Act: -0.1700
Data Index: 8683290 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.3688. Min Act: -0.1700
Data Index: 3144186 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19