Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4406 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0281. Min Range: -7.0281
Max Act: 7.0281. Min Act: -0.1700
Data Index: 7394881 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.9969. Min Act: -0.1700
Data Index: 1434881 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.9031. Min Act: -0.1700
Data Index: 4681256 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.9031. Min Act: -0.1700
Data Index: 288223 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.8719. Min Act: -0.1700
Data Index: 7646861 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.8406. Min Act: -0.1700
Data Index: 8769250 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.8406. Min Act: -0.1700
Data Index: 1796715 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.7781. Min Act: -0.1700
Data Index: 6669822 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.7781. Min Act: -0.1700
Data Index: 436516 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.7469. Min Act: -0.1700
Data Index: 7634079 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.7156. Min Act: -0.1700
Data Index: 6335658 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.7156. Min Act: -0.1700
Data Index: 7561501 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.6844. Min Act: -0.1700
Data Index: 6940511 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.6844. Min Act: -0.1700
Data Index: 3503697 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.6531. Min Act: -0.1700
Data Index: 8055327 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.6219. Min Act: -0.1700
Data Index: 500711 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.6219. Min Act: -0.1700
Data Index: 4307477 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.6219. Min Act: -0.1700
Data Index: 3871832 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.5906. Min Act: -0.1700
Data Index: 5048065 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0281. Min Range: -7.0281
Max Act: 6.5906. Min Act: -0.1700
Data Index: 2569419 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19