Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 630 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.7352. Min Act: -0.1700
Data Index: 2265679 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.6414. Min Act: -0.1700
Data Index: 4635812 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.6102. Min Act: -0.1700
Data Index: 1179227 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.6414. Min Act: -0.1700
Data Index: 1246926 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.6102. Min Act: -0.1700
Data Index: 3772775 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.6102. Min Act: -0.1700
Data Index: 3712019 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5789. Min Act: -0.1700
Data Index: 6284109 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5477. Min Act: -0.1700
Data Index: 5087908 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5477. Min Act: -0.1700
Data Index: 5722375 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5477. Min Act: -0.1700
Data Index: 8580371 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5164. Min Act: -0.1700
Data Index: 5546243 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5164. Min Act: -0.1700
Data Index: 4413023 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.4851. Min Act: -0.1700
Data Index: 1965619 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5164. Min Act: -0.1700
Data Index: 334756 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.4539. Min Act: -0.1700
Data Index: 8259036 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.4539. Min Act: -0.1700
Data Index: 6705532 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.4851. Min Act: -0.1700
Data Index: 7753466 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.4539. Min Act: -0.1700
Data Index: 5932651 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.4226. Min Act: -0.1700
Data Index: 636194 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.4539. Min Act: -0.1700
Data Index: 6917144 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19