Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5154 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1915. Min Range: -7.1915
Max Act: 7.1915. Min Act: -0.1700
Data Index: 3606862 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1915. Min Range: -7.1915
Max Act: 7.1602. Min Act: -0.1700
Data Index: 12144 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1915. Min Range: -7.1915
Max Act: 7.0977. Min Act: -0.1700
Data Index: 2148995 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1915. Min Range: -7.1915
Max Act: 7.0352. Min Act: -0.1700
Data Index: 6002798 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1915. Min Range: -7.1915
Max Act: 7.0040. Min Act: -0.1700
Data Index: 5513958 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.9727. Min Act: -0.1700
Data Index: 7946564 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.9727. Min Act: -0.1700
Data Index: 8197749 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.9727. Min Act: -0.1700
Data Index: 8452067 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.9415. Min Act: -0.1700
Data Index: 4443209 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.9415. Min Act: -0.1700
Data Index: 5893884 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.9102. Min Act: -0.1700
Data Index: 142546 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.8790. Min Act: -0.1700
Data Index: 2999241 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.8790. Min Act: -0.1700
Data Index: 1684075 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.8477. Min Act: -0.1700
Data Index: 1567862 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.8477. Min Act: -0.1700
Data Index: 6976292 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.8477. Min Act: -0.1700
Data Index: 5047603 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.8477. Min Act: -0.1700
Data Index: 2779762 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.8477. Min Act: -0.1700
Data Index: 4272261 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.8477. Min Act: -0.1700
Data Index: 1854632 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1915. Min Range: -7.1915
Max Act: 6.8165. Min Act: -0.1700
Data Index: 762863 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19