Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 955 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.3537. Min Act: -0.1700
Data Index: 2212316 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.3224. Min Act: -0.1700
Data Index: 697871 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.2912. Min Act: -0.1700
Data Index: 1684882 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.2599. Min Act: -0.1700
Data Index: 3798561 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.2599. Min Act: -0.1700
Data Index: 491091 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.2599. Min Act: -0.1700
Data Index: 5423367 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.1349. Min Act: -0.1700
Data Index: 7065689 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.1349. Min Act: -0.1700
Data Index: 857059 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.1037. Min Act: -0.1700
Data Index: 3539058 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.1349. Min Act: -0.1700
Data Index: 525721 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.1037. Min Act: -0.1700
Data Index: 4481998 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.1349. Min Act: -0.1700
Data Index: 5066359 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.1037. Min Act: -0.1700
Data Index: 7410003 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.0412. Min Act: -0.1700
Data Index: 3050125 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.0724. Min Act: -0.1700
Data Index: 1588781 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.0412. Min Act: -0.1700
Data Index: 7595290 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.0412. Min Act: -0.1700
Data Index: 4466683 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.0412. Min Act: -0.1700
Data Index: 1076118 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.0412. Min Act: -0.1700
Data Index: 6578004 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.0412. Min Act: -0.1700
Data Index: 6620659 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19