Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3979 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.9314. Min Act: -0.1700
Data Index: 5407238 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.8376. Min Act: -0.1700
Data Index: 369793 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.7751. Min Act: -0.1700
Data Index: 5459256 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.7439. Min Act: -0.1700
Data Index: 2721716 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.6814. Min Act: -0.1700
Data Index: 2902800 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.6189. Min Act: -0.1700
Data Index: 2470716 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5876. Min Act: -0.1700
Data Index: 6583296 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5564. Min Act: -0.1700
Data Index: 117829 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5564. Min Act: -0.1700
Data Index: 2324146 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5564. Min Act: -0.1700
Data Index: 7924744 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5564. Min Act: -0.1700
Data Index: 7911746 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5251. Min Act: -0.1700
Data Index: 8518077 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4939. Min Act: -0.1700
Data Index: 8169138 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4939. Min Act: -0.1700
Data Index: 7998650 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4626. Min Act: -0.1700
Data Index: 2582569 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4314. Min Act: -0.1700
Data Index: 7230664 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4314. Min Act: -0.1700
Data Index: 7698152 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4314. Min Act: -0.1700
Data Index: 5819392 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.3689. Min Act: -0.1700
Data Index: 7943301 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4001. Min Act: -0.1700
Data Index: 2742011 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19