Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 252 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.6441. Min Act: -0.1700
Data Index: 1975224 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.5816. Min Act: -0.1700
Data Index: 999187 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.3316. Min Act: -0.1700
Data Index: 6229760 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.2691. Min Act: -0.1700
Data Index: 6569680 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.2691. Min Act: -0.1700
Data Index: 1748803 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.1753. Min Act: -0.1700
Data Index: 7321693 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.1753. Min Act: -0.1700
Data Index: 8537534 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.1441. Min Act: -0.1700
Data Index: 5090305 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.1128. Min Act: -0.1700
Data Index: 7813761 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.1128. Min Act: -0.1700
Data Index: 2462029 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.1128. Min Act: -0.1700
Data Index: 6667603 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.1441. Min Act: -0.1700
Data Index: 2667256 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.1128. Min Act: -0.1700
Data Index: 1887324 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.0816. Min Act: -0.1700
Data Index: 6812926 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.0191. Min Act: -0.1700
Data Index: 5968123 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.0191. Min Act: -0.1700
Data Index: 3022986 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.0191. Min Act: -0.1700
Data Index: 489388 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.0191. Min Act: -0.1700
Data Index: 3856986 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6441. Min Range: -7.6441
Max Act: 7.0191. Min Act: -0.1700
Data Index: 812025 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6441. Min Range: -7.6441
Max Act: 6.9878. Min Act: -0.1700
Data Index: 8638724 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19