Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.5501. Min Act: -0.1700
Data Index: 622490 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.3938. Min Act: -0.1700
Data Index: 7667213 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.4251. Min Act: -0.1700
Data Index: 2016083 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.3626. Min Act: -0.1700
Data Index: 6287938 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.3313. Min Act: -0.1700
Data Index: 4300867 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.3313. Min Act: -0.1700
Data Index: 6067879 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.3313. Min Act: -0.1700
Data Index: 915391 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.3313. Min Act: -0.1700
Data Index: 731362 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.3001. Min Act: -0.1700
Data Index: 1846967 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.3001. Min Act: -0.1700
Data Index: 4121513 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2688. Min Act: -0.1700
Data Index: 1174557 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2688. Min Act: -0.1700
Data Index: 4889361 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2688. Min Act: -0.1700
Data Index: 7574697 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2688. Min Act: -0.1700
Data Index: 8237637 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2688. Min Act: -0.1700
Data Index: 425178 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2376. Min Act: -0.1700
Data Index: 2459113 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2376. Min Act: -0.1700
Data Index: 4816655 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2376. Min Act: -0.1700
Data Index: 3944663 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2376. Min Act: -0.1700
Data Index: 6113026 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5501. Min Range: -7.5501
Max Act: 7.2376. Min Act: -0.1700
Data Index: 3085367 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19