Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2756. Min Range: -6.2756
Max Act: 6.2756. Min Act: -0.1700
Data Index: 780401 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2756. Min Range: -6.2756
Max Act: 6.1819. Min Act: -0.1700
Data Index: 2841835 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.9631. Min Act: -0.1700
Data Index: 3645394 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.9319. Min Act: -0.1700
Data Index: 4729933 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.9006. Min Act: -0.1700
Data Index: 1235729 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.8694. Min Act: -0.1700
Data Index: 2755449 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.7756. Min Act: -0.1700
Data Index: 2752498 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.7756. Min Act: -0.1700
Data Index: 285841 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.7444. Min Act: -0.1700
Data Index: 5608049 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.7444. Min Act: -0.1700
Data Index: 3682986 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.7131. Min Act: -0.1700
Data Index: 5563011 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.7131. Min Act: -0.1700
Data Index: 8274254 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.7131. Min Act: -0.1700
Data Index: 5671828 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.7444. Min Act: -0.1700
Data Index: 7969035 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.7131. Min Act: -0.1700
Data Index: 3191456 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.6506. Min Act: -0.1700
Data Index: 1145906 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.6506. Min Act: -0.1700
Data Index: 1171646 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.6506. Min Act: -0.1700
Data Index: 3249918 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.6506. Min Act: -0.1700
Data Index: 1486013 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2756. Min Range: -6.2756
Max Act: 5.6194. Min Act: -0.1700
Data Index: 1064790 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19