Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5628 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.7673. Min Act: -0.1700
Data Index: 7854412 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.6423. Min Act: -0.1700
Data Index: 2020642 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.6423. Min Act: -0.1700
Data Index: 4974788 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.5798. Min Act: -0.1700
Data Index: 7723885 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.4548. Min Act: -0.1700
Data Index: 1692486 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.3923. Min Act: -0.1700
Data Index: 7693932 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.3298. Min Act: -0.1700
Data Index: 7693930 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.2673. Min Act: -0.1700
Data Index: 5582623 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.2048. Min Act: -0.1700
Data Index: 2319545 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.2673. Min Act: -0.1700
Data Index: 7693923 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.2048. Min Act: -0.1700
Data Index: 6265835 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.0798. Min Act: -0.1700
Data Index: 7649856 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.0173. Min Act: -0.1700
Data Index: 4974784 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.0173. Min Act: -0.1700
Data Index: 1319529 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.7673. Min Range: -15.7673
Max Act: 15.0798. Min Act: -0.1700
Data Index: 6040117 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.7673. Min Range: -15.7673
Max Act: 14.8923. Min Act: -0.1700
Data Index: 4905510 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.7673. Min Range: -15.7673
Max Act: 14.8923. Min Act: -0.1700
Data Index: 5722734 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.7673. Min Range: -15.7673
Max Act: 14.7673. Min Act: -0.1700
Data Index: 8131977 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.7673. Min Range: -15.7673
Max Act: 14.8298. Min Act: -0.1700
Data Index: 1547748 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.7673. Min Range: -15.7673
Max Act: 14.7673. Min Act: -0.1700
Data Index: 7686963 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19