Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6372 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.8024. Min Act: -0.1700
Data Index: 4303488 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.6774. Min Act: -0.1700
Data Index: 5960623 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.5524. Min Act: -0.1700
Data Index: 3670698 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.4274. Min Act: -0.1700
Data Index: 12019 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.3649. Min Act: -0.1700
Data Index: 2940589 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.3024. Min Act: -0.1700
Data Index: 424053 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.3024. Min Act: -0.1700
Data Index: 3132703 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.2399. Min Act: -0.1700
Data Index: 5959756 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.1774. Min Act: -0.1700
Data Index: 738110 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.1774. Min Act: -0.1700
Data Index: 1723516 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.1774. Min Act: -0.1700
Data Index: 272587 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.1149. Min Act: -0.1700
Data Index: 1697108 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.1149. Min Act: -0.1700
Data Index: 5061523 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.1149. Min Act: -0.1700
Data Index: 6049861 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.1149. Min Act: -0.1700
Data Index: 7592566 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.1149. Min Act: -0.1700
Data Index: 8154294 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.0524. Min Act: -0.1700
Data Index: 7801503 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8024. Min Range: -8.8024
Max Act: 7.9899. Min Act: -0.1700
Data Index: 4126113 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.0524. Min Act: -0.1700
Data Index: 4549621 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8024. Min Range: -8.8024
Max Act: 8.0524. Min Act: -0.1700
Data Index: 6333625 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19