Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.5979. Min Act: -0.1700
Data Index: 7279730 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.4729. Min Act: -0.1700
Data Index: 1895416 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.4729. Min Act: -0.1700
Data Index: 2113724 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.4104. Min Act: -0.1700
Data Index: 675625 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.4104. Min Act: -0.1700
Data Index: 3442593 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.4104. Min Act: -0.1700
Data Index: 2169441 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.4104. Min Act: -0.1700
Data Index: 1210374 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.4104. Min Act: -0.1700
Data Index: 3769983 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3479. Min Act: -0.1700
Data Index: 5561699 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3792. Min Act: -0.1700
Data Index: 6048324 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3792. Min Act: -0.1700
Data Index: 1529520 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3479. Min Act: -0.1700
Data Index: 8348037 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3479. Min Act: -0.1700
Data Index: 8640965 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3479. Min Act: -0.1700
Data Index: 2941212 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3479. Min Act: -0.1700
Data Index: 6205659 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3479. Min Act: -0.1700
Data Index: 3580073 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3167. Min Act: -0.1700
Data Index: 8441165 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3167. Min Act: -0.1700
Data Index: 30759 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3167. Min Act: -0.1700
Data Index: 3901476 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5979. Min Range: -5.5979
Max Act: 5.3167. Min Act: -0.1700
Data Index: 3969090 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19