Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.2479. Min Act: -0.1700
Data Index: 6246355 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.2479. Min Act: -0.1700
Data Index: 5597160 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.0917. Min Act: -0.1700
Data Index: 2852768 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9979. Min Act: -0.1700
Data Index: 4771762 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9979. Min Act: -0.1700
Data Index: 4453845 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9354. Min Act: -0.1700
Data Index: 1146160 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9667. Min Act: -0.1700
Data Index: 716436 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9354. Min Act: -0.1700
Data Index: 5901105 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9354. Min Act: -0.1700
Data Index: 8820 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9042. Min Act: -0.1700
Data Index: 6269930 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8729. Min Act: -0.1700
Data Index: 4552563 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8729. Min Act: -0.1700
Data Index: 2478924 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8417. Min Act: -0.1700
Data Index: 6408523 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8104. Min Act: -0.1700
Data Index: 6561412 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.7792. Min Act: -0.1700
Data Index: 6222320 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8104. Min Act: -0.1700
Data Index: 1789548 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8104. Min Act: -0.1700
Data Index: 4020626 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.7792. Min Act: -0.1700
Data Index: 1896528 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8104. Min Act: -0.1700
Data Index: 1637426 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8104. Min Act: -0.1700
Data Index: 2430463 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19