Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.6106. Min Act: -0.1700
Data Index: 7411390 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.6106. Min Act: -0.1700
Data Index: 4375723 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4853. Min Act: -0.1700
Data Index: 6059400 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4853. Min Act: -0.1700
Data Index: 7571049 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4853. Min Act: -0.1700
Data Index: 5363958 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4853. Min Act: -0.1700
Data Index: 5562611 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4540. Min Act: -0.1700
Data Index: 3603078 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4540. Min Act: -0.1700
Data Index: 4025434 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4540. Min Act: -0.1700
Data Index: 3904962 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4226. Min Act: -0.1700
Data Index: 8628858 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4540. Min Act: -0.1700
Data Index: 342123 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4540. Min Act: -0.1700
Data Index: 7393368 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4540. Min Act: -0.1700
Data Index: 7583154 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4226. Min Act: -0.1699
Data Index: 7749226 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.3913. Min Act: -0.1700
Data Index: 1094857 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4540. Min Act: -0.1700
Data Index: 342112 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.4226. Min Act: -0.1700
Data Index: 141369 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.3913. Min Act: -0.1700
Data Index: 4350871 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.3913. Min Act: -0.1700
Data Index: 5734109 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6106. Min Range: -3.6106
Max Act: 3.3913. Min Act: -0.1700
Data Index: 3515519 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19