Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4822 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.7130. Min Act: -0.1700
Data Index: 1941912 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.7130. Min Act: -0.1700
Data Index: 1200678 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.5880. Min Act: -0.1700
Data Index: 7287463 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.5568. Min Act: -0.1700
Data Index: 2981389 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.5255. Min Act: -0.1700
Data Index: 7645889 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.4943. Min Act: -0.1700
Data Index: 8638206 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.4630. Min Act: -0.1700
Data Index: 5234464 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.4630. Min Act: -0.1700
Data Index: 5363846 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.4318. Min Act: -0.1700
Data Index: 5653721 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.4318. Min Act: -0.1700
Data Index: 7499155 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.4318. Min Act: -0.1700
Data Index: 4685716 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.4318. Min Act: -0.1700
Data Index: 6743009 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.3693. Min Act: -0.1700
Data Index: 988019 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.3693. Min Act: -0.1700
Data Index: 6901653 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.3693. Min Act: -0.1700
Data Index: 8101026 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.3693. Min Act: -0.1700
Data Index: 539351 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.3380. Min Act: -0.1700
Data Index: 3905171 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.3693. Min Act: -0.1700
Data Index: 4788447 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.3068. Min Act: -0.1700
Data Index: 4096498 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7130. Min Range: -4.7130
Max Act: 4.3380. Min Act: -0.1700
Data Index: 58251 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19