Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0952. Min Act: -0.1700
Data Index: 1090033 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.1264. Min Act: -0.1700
Data Index: 627787 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.1264. Min Act: -0.1700
Data Index: 2291030 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0952. Min Act: -0.1700
Data Index: 5417587 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0952. Min Act: -0.1700
Data Index: 1090026 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0952. Min Act: -0.1700
Data Index: 3982617 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 1611501 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 422732 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 1479511 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 8729480 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 3818313 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 8416461 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0327. Min Act: -0.1700
Data Index: 3766007 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 7237708 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0327. Min Act: -0.1700
Data Index: 3561859 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 2963698 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 5762604 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0639. Min Act: -0.1700
Data Index: 5483966 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0327. Min Act: -0.1700
Data Index: 4049290 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1264. Min Range: -4.1264
Max Act: 4.0327. Min Act: -0.1700
Data Index: 4108022 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19