Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 664 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3423. Min Range: -8.3423
Max Act: 8.3423. Min Act: -0.1700
Data Index: 157908 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3423. Min Range: -8.3423
Max Act: 8.2173. Min Act: -0.1700
Data Index: 3166194 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3423. Min Range: -8.3423
Max Act: 8.1548. Min Act: -0.1700
Data Index: 1919933 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.8423. Min Act: -0.1700
Data Index: 665733 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.7173. Min Act: -0.1700
Data Index: 8346251 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.7173. Min Act: -0.1700
Data Index: 6844104 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.6860. Min Act: -0.1700
Data Index: 1627779 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.6860. Min Act: -0.1700
Data Index: 7068994 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.6548. Min Act: -0.1700
Data Index: 5325759 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.6548. Min Act: -0.1700
Data Index: 836852 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.5923. Min Act: -0.1700
Data Index: 2454584 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.5610. Min Act: -0.1700
Data Index: 5582844 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.5298. Min Act: -0.1700
Data Index: 6516093 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.4673. Min Act: -0.1700
Data Index: 8037518 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.4673. Min Act: -0.1700
Data Index: 2830301 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.4048. Min Act: -0.1700
Data Index: 864764 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.3735. Min Act: -0.1700
Data Index: 8551641 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.3735. Min Act: -0.1700
Data Index: 4611956 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.3423. Min Act: -0.1700
Data Index: 6941943 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3423. Min Range: -8.3423
Max Act: 7.2798. Min Act: -0.1700
Data Index: 3838841 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19