Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 106 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.9088. Min Act: -0.1700
Data Index: 8252434 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.7838. Min Act: -0.1700
Data Index: 7501877 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.7213. Min Act: -0.1700
Data Index: 5647286 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.6588. Min Act: -0.1680
Data Index: 3986601 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.5025. Min Act: -0.1700
Data Index: 4330821 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.4400. Min Act: -0.1700
Data Index: 7460325 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.4088. Min Act: -0.1700
Data Index: 1046147 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.4400. Min Act: -0.1700
Data Index: 6973807 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.4088. Min Act: -0.1700
Data Index: 7577773 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.4088. Min Act: -0.1693
Data Index: 3986606 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.4088. Min Act: -0.1700
Data Index: 5647287 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.3775. Min Act: -0.1700
Data Index: 4124800 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.3775. Min Act: -0.1700
Data Index: 2823633 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.3463. Min Act: -0.1700
Data Index: 7577763 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.3463. Min Act: -0.1652
Data Index: 8252429 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.3150. Min Act: -0.1700
Data Index: 8761290 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.2838. Min Act: -0.1692
Data Index: 5815568 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.3150. Min Act: -0.1695
Data Index: 3986605 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.3150. Min Act: -0.1698
Data Index: 1553498 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9088. Min Range: -5.9088
Max Act: 5.3150. Min Act: -0.1700
Data Index: 1418942 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19