Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2145. Min Range: -8.2145
Max Act: 8.2145. Min Act: -0.1700
Data Index: 5539466 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.6520. Min Act: -0.1700
Data Index: 5134802 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.5895. Min Act: -0.1700
Data Index: 6328878 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.5582. Min Act: -0.1700
Data Index: 5592448 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.5582. Min Act: -0.1700
Data Index: 6568622 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.4957. Min Act: -0.1700
Data Index: 5896197 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.4645. Min Act: -0.1700
Data Index: 2575408 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.4332. Min Act: -0.1700
Data Index: 7252646 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.4332. Min Act: -0.1700
Data Index: 8547525 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.3707. Min Act: -0.1700
Data Index: 682518 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.3707. Min Act: -0.1700
Data Index: 4363675 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.3395. Min Act: -0.1700
Data Index: 7700171 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.3707. Min Act: -0.1700
Data Index: 5677538 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.3082. Min Act: -0.1700
Data Index: 6262267 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.2770. Min Act: -0.1700
Data Index: 869382 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.2770. Min Act: -0.1700
Data Index: 2489718 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.2457. Min Act: -0.1700
Data Index: 4047729 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.2457. Min Act: -0.1700
Data Index: 3133265 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.2145. Min Act: -0.1700
Data Index: 1949426 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2145. Min Range: -8.2145
Max Act: 7.1832. Min Act: -0.1700
Data Index: 6994909 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19