Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7701. Min Range: -6.7701
Max Act: 6.7701. Min Act: -0.1700
Data Index: 1257787 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7701. Min Range: -6.7701
Max Act: 6.3326. Min Act: -0.1700
Data Index: 4459905 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7701. Min Range: -6.7701
Max Act: 6.2389. Min Act: -0.1700
Data Index: 5361092 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7701. Min Range: -6.7701
Max Act: 6.2076. Min Act: -0.1700
Data Index: 2918231 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7701. Min Range: -6.7701
Max Act: 6.1451. Min Act: -0.1700
Data Index: 6302023 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7701. Min Range: -6.7701
Max Act: 6.0826. Min Act: -0.1700
Data Index: 5373229 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7701. Min Range: -6.7701
Max Act: 6.0826. Min Act: -0.1700
Data Index: 3899266 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7701. Min Range: -6.7701
Max Act: 6.0826. Min Act: -0.1700
Data Index: 6421366 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.9576. Min Act: -0.1700
Data Index: 6418123 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.8639. Min Act: -0.1700
Data Index: 2698563 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.8951. Min Act: -0.1700
Data Index: 2392142 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.8639. Min Act: -0.1700
Data Index: 7689138 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.8326. Min Act: -0.1700
Data Index: 8270225 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.7701. Min Act: -0.1700
Data Index: 5397270 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.7389. Min Act: -0.1700
Data Index: 1317900 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.7701. Min Act: -0.1700
Data Index: 3635615 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.7701. Min Act: -0.1700
Data Index: 4830095 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.7701. Min Act: -0.1700
Data Index: 1933307 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.7389. Min Act: -0.1700
Data Index: 2866905 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7701. Min Range: -6.7701
Max Act: 5.7389. Min Act: -0.1700
Data Index: 2541138 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19