Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3987 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.7130. Min Act: -0.1700
Data Index: 6749591 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.5880. Min Act: -0.1700
Data Index: 945287 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.5880. Min Act: -0.1700
Data Index: 8794494 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.5567. Min Act: -0.1700
Data Index: 6471961 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.5567. Min Act: -0.1700
Data Index: 8774491 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.5255. Min Act: -0.1700
Data Index: 7755627 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.5255. Min Act: -0.1700
Data Index: 7074018 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.5255. Min Act: -0.1700
Data Index: 80453 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.4942. Min Act: -0.1700
Data Index: 2737397 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.5255. Min Act: -0.1700
Data Index: 2275277 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.4630. Min Act: -0.1700
Data Index: 2117255 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.4317. Min Act: -0.1700
Data Index: 1334360 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.4317. Min Act: -0.1700
Data Index: 7902547 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.4005. Min Act: -0.1700
Data Index: 474422 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.4005. Min Act: -0.1700
Data Index: 4643301 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.3380. Min Act: -0.1700
Data Index: 388897 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.3067. Min Act: -0.1700
Data Index: 5812880 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.3067. Min Act: -0.1700
Data Index: 5943530 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.2755. Min Act: -0.1700
Data Index: 2033978 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.3067. Min Act: -0.1700
Data Index: 1176136 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19