Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5640 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.5678. Min Act: -0.1700
Data Index: 5426581 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.4741. Min Act: -0.1700
Data Index: 7687183 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.4741. Min Act: -0.1700
Data Index: 7394908 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.4428. Min Act: -0.1700
Data Index: 3671971 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.3803. Min Act: -0.1700
Data Index: 8095123 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.3803. Min Act: -0.1700
Data Index: 5518495 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2866. Min Act: -0.1700
Data Index: 1897800 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.3178. Min Act: -0.1700
Data Index: 2599754 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2866. Min Act: -0.1700
Data Index: 3265480 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2866. Min Act: -0.1700
Data Index: 6367118 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2553. Min Act: -0.1700
Data Index: 762069 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2553. Min Act: -0.1700
Data Index: 8813586 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2553. Min Act: -0.1700
Data Index: 7309228 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2241. Min Act: -0.1700
Data Index: 6377019 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2241. Min Act: -0.1700
Data Index: 8699283 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2241. Min Act: -0.1700
Data Index: 3955474 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.2241. Min Act: -0.1700
Data Index: 2424351 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.1928. Min Act: -0.1700
Data Index: 1082111 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.1928. Min Act: -0.1700
Data Index: 8056502 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5678. Min Range: -6.5678
Max Act: 6.1928. Min Act: -0.1700
Data Index: 2171662 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19