Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.8649. Min Act: -0.1700
Data Index: 3724913 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.8337. Min Act: -0.1700
Data Index: 4325777 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.7087. Min Act: -0.1700
Data Index: 816010 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.6462. Min Act: -0.1700
Data Index: 8668832 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.5524. Min Act: -0.1700
Data Index: 793702 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.5837. Min Act: -0.1700
Data Index: 3513607 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.5837. Min Act: -0.1700
Data Index: 5363040 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.5212. Min Act: -0.1700
Data Index: 2146540 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.4899. Min Act: -0.1700
Data Index: 508203 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.3962. Min Act: -0.1700
Data Index: 2841227 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.3337. Min Act: -0.1700
Data Index: 2907163 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.3337. Min Act: -0.1700
Data Index: 6381509 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.3024. Min Act: -0.1700
Data Index: 4014469 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.2712. Min Act: -0.1700
Data Index: 8488120 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.3024. Min Act: -0.1700
Data Index: 6246629 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.2399. Min Act: -0.1700
Data Index: 1923900 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.3024. Min Act: -0.1700
Data Index: 484243 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.2087. Min Act: -0.1700
Data Index: 1507656 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.2087. Min Act: -0.1700
Data Index: 7126179 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8649. Min Range: -6.8649
Max Act: 6.1774. Min Act: -0.1700
Data Index: 8636147 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19