Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3297 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1802. Min Range: -8.1802
Max Act: 8.1802. Min Act: -0.1700
Data Index: 7418448 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.8677. Min Act: -0.1700
Data Index: 2893820 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.8677. Min Act: -0.1700
Data Index: 4904267 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.8677. Min Act: -0.1700
Data Index: 8460284 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.6177. Min Act: -0.1700
Data Index: 4468904 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.5864. Min Act: -0.1700
Data Index: 3775551 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.5239. Min Act: -0.1700
Data Index: 4904269 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.4302. Min Act: -0.1700
Data Index: 4904270 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.4302. Min Act: -0.1700
Data Index: 4904271 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.3989. Min Act: -0.1700
Data Index: 2598611 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.3989. Min Act: -0.1700
Data Index: 2006144 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.3677. Min Act: -0.1700
Data Index: 3037445 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.3677. Min Act: -0.1700
Data Index: 2072854 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.3364. Min Act: -0.1700
Data Index: 3525941 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.3364. Min Act: -0.1700
Data Index: 7754251 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.2427. Min Act: -0.1700
Data Index: 2671866 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.2427. Min Act: -0.1700
Data Index: 651447 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.1802. Min Act: -0.1700
Data Index: 314400 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.1802. Min Act: -0.1700
Data Index: 4226715 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1802. Min Range: -8.1802
Max Act: 7.1802. Min Act: -0.1700
Data Index: 5586927 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19