Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.6938. Min Act: -0.1700
Data Index: 3116165 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.5376. Min Act: -0.1700
Data Index: 6596143 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.3501. Min Act: -0.1700
Data Index: 1913357 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.3188. Min Act: -0.1700
Data Index: 7721980 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.2563. Min Act: -0.1700
Data Index: 6079251 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.2563. Min Act: -0.1700
Data Index: 6998664 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.2251. Min Act: -0.1700
Data Index: 673614 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.1938. Min Act: -0.1700
Data Index: 5208774 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.1626. Min Act: -0.1700
Data Index: 840599 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.1938. Min Act: -0.1700
Data Index: 1407115 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.1313. Min Act: -0.1700
Data Index: 218112 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.1313. Min Act: -0.1700
Data Index: 4379662 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.1626. Min Act: -0.1700
Data Index: 461097 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.1001. Min Act: -0.1700
Data Index: 1030666 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.1001. Min Act: -0.1700
Data Index: 466927 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.0688. Min Act: -0.1700
Data Index: 3796796 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.0688. Min Act: -0.1700
Data Index: 2146922 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.0376. Min Act: -0.1700
Data Index: 6162238 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.0376. Min Act: -0.1700
Data Index: 2722824 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6938. Min Range: -7.6938
Max Act: 7.0063. Min Act: -0.1700
Data Index: 1990247 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19