Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1046 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.8798. Min Act: -0.1700
Data Index: 4440412 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.8173. Min Act: -0.1700
Data Index: 2318783 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.6923. Min Act: -0.1700
Data Index: 1922114 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.6923. Min Act: -0.1700
Data Index: 412224 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.6298. Min Act: -0.1700
Data Index: 8136750 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.6298. Min Act: -0.1700
Data Index: 4770786 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.6298. Min Act: -0.1700
Data Index: 8784715 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.4423. Min Act: -0.1700
Data Index: 2807118 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.3798. Min Act: -0.1700
Data Index: 5563509 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.3173. Min Act: -0.1700
Data Index: 7287961 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.3798. Min Act: -0.1700
Data Index: 2653230 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.3173. Min Act: -0.1700
Data Index: 3883699 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.2548. Min Act: -0.1700
Data Index: 2351344 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.1298. Min Act: -0.1700
Data Index: 5474513 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.1298. Min Act: -0.1700
Data Index: 2628931 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.0673. Min Act: -0.1700
Data Index: 4920038 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.0360. Min Act: -0.1700
Data Index: 6428672 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.0673. Min Act: -0.1700
Data Index: 5138494 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.0673. Min Act: -0.1700
Data Index: 1133088 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8798. Min Range: -8.8798
Max Act: 8.0673. Min Act: -0.1700
Data Index: 8034495 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19