Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.0852. Min Act: -0.1700
Data Index: 6709707 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.1477. Min Act: -0.1700
Data Index: 3560118 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.1477. Min Act: -0.1700
Data Index: 4114735 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.1477. Min Act: -0.1700
Data Index: 5943652 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.2102. Min Act: -0.1700
Data Index: 9814 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.0539. Min Act: -0.1700
Data Index: 8595257 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.0227. Min Act: -0.1700
Data Index: 5355800 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.0227. Min Act: -0.1700
Data Index: 544732 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.9602. Min Act: -0.1700
Data Index: 1645978 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.9914. Min Act: -0.1700
Data Index: 2979173 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.9602. Min Act: -0.1700
Data Index: 668370 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.9289. Min Act: -0.1700
Data Index: 1830248 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.9289. Min Act: -0.1700
Data Index: 6291406 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8977. Min Act: -0.1700
Data Index: 29501 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8664. Min Act: -0.1700
Data Index: 8583351 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8664. Min Act: -0.1700
Data Index: 2688072 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8664. Min Act: -0.1700
Data Index: 7379201 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8352. Min Act: -0.1700
Data Index: 4491199 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8352. Min Act: -0.1700
Data Index: 3379005 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8352. Min Act: -0.1700
Data Index: 2907188 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19