Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1891 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.2910. Min Act: -0.1700
Data Index: 7074449 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.2910. Min Act: -0.1700
Data Index: 7197152 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1660. Min Act: -0.1700
Data Index: 5426395 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1660. Min Act: -0.1700
Data Index: 2184773 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.8848. Min Act: -0.1700
Data Index: 2181099 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.8848. Min Act: -0.1700
Data Index: 4058542 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.8535. Min Act: -0.1700
Data Index: 6440663 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.8535. Min Act: -0.1700
Data Index: 2570751 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.8223. Min Act: -0.1700
Data Index: 6856078 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.8535. Min Act: -0.1700
Data Index: 616698 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.8223. Min Act: -0.1700
Data Index: 1274208 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.7910. Min Act: -0.1700
Data Index: 1753478 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.6973. Min Act: -0.1700
Data Index: 6609785 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.7598. Min Act: -0.1700
Data Index: 1361349 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.7285. Min Act: -0.1700
Data Index: 5254684 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.7285. Min Act: -0.1700
Data Index: 6082687 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.6973. Min Act: -0.1700
Data Index: 4001060 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.6660. Min Act: -0.1700
Data Index: 2932467 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.6973. Min Act: -0.1700
Data Index: 6152485 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.6660. Min Act: -0.1700
Data Index: 4114406 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19