Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2045 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.8863. Min Act: -0.1700
Data Index: 4791891 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.7613. Min Act: -0.1700
Data Index: 804787 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.7613. Min Act: -0.1700
Data Index: 6560428 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.7613. Min Act: -0.1700
Data Index: 4822289 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.6988. Min Act: -0.1700
Data Index: 113260 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.5738. Min Act: -0.1700
Data Index: 2398016 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.5113. Min Act: -0.1700
Data Index: 5263556 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.4488. Min Act: -0.1700
Data Index: 3305956 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.3863. Min Act: -0.1700
Data Index: 8414938 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.3238. Min Act: -0.1700
Data Index: 647341 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.3238. Min Act: -0.1700
Data Index: 6580670 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.3238. Min Act: -0.1700
Data Index: 5763567 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.2613. Min Act: -0.1700
Data Index: 1444823 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.2613. Min Act: -0.1700
Data Index: 2261729 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.1988. Min Act: -0.1700
Data Index: 1715882 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.1988. Min Act: -0.1700
Data Index: 4761041 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.1363. Min Act: -0.1700
Data Index: 6411017 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.1363. Min Act: -0.1700
Data Index: 8141063 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.1363. Min Act: -0.1700
Data Index: 6494104 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8863. Min Range: -8.8863
Max Act: 8.0738. Min Act: -0.1700
Data Index: 2286026 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19