Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.6331. Min Act: -0.1700
Data Index: 367277 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.4768. Min Act: -0.1700
Data Index: 1113150 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.2893. Min Act: -0.1700
Data Index: 2020499 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.1643. Min Act: -0.1700
Data Index: 2918791 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.1643. Min Act: -0.1700
Data Index: 938379 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.1018. Min Act: -0.1700
Data Index: 3790155 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.1331. Min Act: -0.1700
Data Index: 5372933 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.0706. Min Act: -0.1700
Data Index: 7603822 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.0393. Min Act: -0.1700
Data Index: 6028723 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.0393. Min Act: -0.1700
Data Index: 1708649 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.0081. Min Act: -0.1700
Data Index: 410554 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.0081. Min Act: -0.1700
Data Index: 3550360 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.9768. Min Act: -0.1700
Data Index: 4759924 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.9768. Min Act: -0.1700
Data Index: 6103105 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.0081. Min Act: -0.1700
Data Index: 3820402 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.9768. Min Act: -0.1700
Data Index: 2191386 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.9456. Min Act: -0.1700
Data Index: 7461631 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.9456. Min Act: -0.1700
Data Index: 2304830 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.8831. Min Act: -0.1700
Data Index: 4110923 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.8831. Min Act: -0.1700
Data Index: 14318 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19