Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 894 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.4534. Min Act: -0.1700
Data Index: 2465798 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.4222. Min Act: -0.1700
Data Index: 8693417 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.4222. Min Act: -0.1700
Data Index: 7707170 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.3909. Min Act: -0.1700
Data Index: 6162876 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.3909. Min Act: -0.1700
Data Index: 8485607 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.4222. Min Act: -0.1700
Data Index: 1636423 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.3909. Min Act: -0.1700
Data Index: 4140425 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.3597. Min Act: -0.1700
Data Index: 8618378 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.3597. Min Act: -0.1700
Data Index: 7187916 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.3284. Min Act: -0.1700
Data Index: 7042934 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.2972. Min Act: -0.1700
Data Index: 7981569 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.3284. Min Act: -0.1700
Data Index: 5773817 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.2972. Min Act: -0.1700
Data Index: 281589 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.2659. Min Act: -0.1700
Data Index: 8618379 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.2972. Min Act: -0.1700
Data Index: 536391 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.2659. Min Act: -0.1700
Data Index: 6059056 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.2659. Min Act: -0.1700
Data Index: 4874737 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.2347. Min Act: -0.1700
Data Index: 1056561 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.2659. Min Act: -0.1700
Data Index: 6731087 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4534. Min Range: -5.4534
Max Act: 5.2659. Min Act: -0.1700
Data Index: 41004 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19