Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.6454. Min Act: -0.1700
Data Index: 6216717 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.6141. Min Act: -0.1700
Data Index: 973637 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.5829. Min Act: -0.1700
Data Index: 4094869 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.5204. Min Act: -0.1700
Data Index: 3887678 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.4891. Min Act: -0.1700
Data Index: 1705818 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.4891. Min Act: -0.1700
Data Index: 7190003 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.4579. Min Act: -0.1700
Data Index: 1670656 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.4579. Min Act: -0.1700
Data Index: 910924 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3954. Min Act: -0.1700
Data Index: 6353089 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.4266. Min Act: -0.1700
Data Index: 4152559 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.4266. Min Act: -0.1700
Data Index: 348104 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3954. Min Act: -0.1700
Data Index: 7822900 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3954. Min Act: -0.1700
Data Index: 1631296 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3954. Min Act: -0.1700
Data Index: 6614288 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3954. Min Act: -0.1700
Data Index: 6632542 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3329. Min Act: -0.1700
Data Index: 85035 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3329. Min Act: -0.1700
Data Index: 6780873 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3016. Min Act: -0.1700
Data Index: 1994180 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3329. Min Act: -0.1700
Data Index: 5193639 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6454. Min Range: -4.6454
Max Act: 4.3329. Min Act: -0.1700
Data Index: 1631280 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19