Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.6699. Min Act: -0.1700
Data Index: 4757045 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.6543. Min Act: -0.1700
Data Index: 5796450 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.6386. Min Act: -0.1700
Data Index: 4869749 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.6230. Min Act: -0.1700
Data Index: 2106927 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.5917. Min Act: -0.1700
Data Index: 3525089 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.6073. Min Act: -0.1700
Data Index: 5526786 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.6073. Min Act: -0.1700
Data Index: 6642778 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.5290. Min Act: -0.1700
Data Index: 259250 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4977. Min Act: -0.1700
Data Index: 3954830 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4977. Min Act: -0.1700
Data Index: 6407831 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4664. Min Act: -0.1700
Data Index: 8223990 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4194. Min Act: -0.1700
Data Index: 3751120 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4351. Min Act: -0.1700
Data Index: 3833269 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4351. Min Act: -0.1700
Data Index: 4834512 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4194. Min Act: -0.1700
Data Index: 1563820 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4037. Min Act: -0.1700
Data Index: 378909 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4037. Min Act: -0.1700
Data Index: 7403767 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.4037. Min Act: -0.1700
Data Index: 311935 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.3723. Min Act: -0.1700
Data Index: 1474023 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6699. Min Range: -3.6699
Max Act: 3.3723. Min Act: -0.1700
Data Index: 264480 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19