Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2354. Min Range: -8.2354
Max Act: 8.2354. Min Act: -0.1700
Data Index: 2428824 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2354. Min Range: -8.2354
Max Act: 8.2042. Min Act: -0.1700
Data Index: 8709722 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.9854. Min Act: -0.1700
Data Index: 6528835 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.9854. Min Act: -0.1700
Data Index: 7143990 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.8292. Min Act: -0.1700
Data Index: 6638752 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.7667. Min Act: -0.1700
Data Index: 6552284 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.7979. Min Act: -0.1700
Data Index: 3945832 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.7979. Min Act: -0.1700
Data Index: 344696 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.7667. Min Act: -0.1700
Data Index: 6797900 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.6417. Min Act: -0.1700
Data Index: 979548 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.6104. Min Act: -0.1700
Data Index: 336765 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.5792. Min Act: -0.1700
Data Index: 4977842 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.5792. Min Act: -0.1700
Data Index: 1959505 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.5479. Min Act: -0.1700
Data Index: 6649607 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.5479. Min Act: -0.1700
Data Index: 4251229 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.5479. Min Act: -0.1700
Data Index: 2601798 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.5479. Min Act: -0.1700
Data Index: 7985180 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.5479. Min Act: -0.1700
Data Index: 3914003 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.5167. Min Act: -0.1700
Data Index: 2068253 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2354. Min Range: -8.2354
Max Act: 7.5167. Min Act: -0.1700
Data Index: 4345441 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19