Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4234 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3798. Min Range: -8.3798
Max Act: 8.3798. Min Act: -0.1700
Data Index: 2648468 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3798. Min Range: -8.3798
Max Act: 8.1298. Min Act: -0.1700
Data Index: 7280362 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3798. Min Range: -8.3798
Max Act: 8.1298. Min Act: -0.1700
Data Index: 7531459 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3798. Min Range: -8.3798
Max Act: 8.0673. Min Act: -0.1700
Data Index: 6810698 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3798. Min Range: -8.3798
Max Act: 8.0048. Min Act: -0.1700
Data Index: 758818 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.9423. Min Act: -0.1700
Data Index: 352717 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.9423. Min Act: -0.1700
Data Index: 877721 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.9110. Min Act: -0.1700
Data Index: 8225648 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.8485. Min Act: -0.1700
Data Index: 6709331 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.8173. Min Act: -0.1700
Data Index: 8494454 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.7548. Min Act: -0.1700
Data Index: 2200668 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.7235. Min Act: -0.1700
Data Index: 1411593 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.7235. Min Act: -0.1700
Data Index: 6248800 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.6923. Min Act: -0.1700
Data Index: 2200665 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.7235. Min Act: -0.1700
Data Index: 5738265 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.6923. Min Act: -0.1700
Data Index: 2626532 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.6610. Min Act: -0.1700
Data Index: 4830922 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.5985. Min Act: -0.1700
Data Index: 4202522 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.5985. Min Act: -0.1700
Data Index: 1443490 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3798. Min Range: -8.3798
Max Act: 7.5985. Min Act: -0.1700
Data Index: 5453218 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19