Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4607 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.6962. Min Act: -0.1700
Data Index: 8015771 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.6962. Min Act: -0.1700
Data Index: 306993 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.6649. Min Act: -0.1700
Data Index: 3674119 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.6337. Min Act: -0.1700
Data Index: 4369474 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.6649. Min Act: -0.1700
Data Index: 4576325 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.5399. Min Act: -0.1700
Data Index: 8031839 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.5087. Min Act: -0.1700
Data Index: 7771889 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.5087. Min Act: -0.1700
Data Index: 2024155 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.5087. Min Act: -0.1700
Data Index: 182828 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.5087. Min Act: -0.1700
Data Index: 7750216 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.5087. Min Act: -0.1700
Data Index: 5448313 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.4462. Min Act: -0.1700
Data Index: 5163042 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.4462. Min Act: -0.1700
Data Index: 5743898 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.4462. Min Act: -0.1700
Data Index: 8241282 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.4149. Min Act: -0.1700
Data Index: 7441893 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.4149. Min Act: -0.1700
Data Index: 7999666 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.3524. Min Act: -0.1700
Data Index: 4683670 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.3524. Min Act: -0.1700
Data Index: 3944686 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.3524. Min Act: -0.1700
Data Index: 7360410 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6962. Min Range: -7.6962
Max Act: 7.3524. Min Act: -0.1700
Data Index: 5782541 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19