Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5277. Min Range: -9.5277
Max Act: 9.5277. Min Act: -0.1700
Data Index: 8155787 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5277. Min Range: -9.5277
Max Act: 9.0902. Min Act: -0.1700
Data Index: 2187845 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5277. Min Range: -9.5277
Max Act: 9.0277. Min Act: -0.1700
Data Index: 5084127 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.9027. Min Act: -0.1700
Data Index: 437647 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.7777. Min Act: -0.1700
Data Index: 1586623 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.6527. Min Act: -0.1700
Data Index: 1688899 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.4652. Min Act: -0.1700
Data Index: 3698390 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.4652. Min Act: -0.1700
Data Index: 4846920 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.4652. Min Act: -0.1700
Data Index: 6303496 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.4027. Min Act: -0.1700
Data Index: 8798862 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.4027. Min Act: -0.1700
Data Index: 3122709 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.3402. Min Act: -0.1700
Data Index: 6019648 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.2777. Min Act: -0.1700
Data Index: 4126050 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.2152. Min Act: -0.1700
Data Index: 535575 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.1527. Min Act: -0.1700
Data Index: 4349725 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.0902. Min Act: -0.1700
Data Index: 4593553 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.1527. Min Act: -0.1700
Data Index: 4846925 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.1527. Min Act: -0.1700
Data Index: 1320257 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.0902. Min Act: -0.1700
Data Index: 6172610 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5277. Min Range: -9.5277
Max Act: 8.0902. Min Act: -0.1700
Data Index: 5033218 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19