Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 132 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5924. Min Range: -12.5924
Max Act: 12.5924. Min Act: -0.1699
Data Index: 7420599 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5924. Min Range: -12.5924
Max Act: 12.4049. Min Act: -0.1700
Data Index: 6681751 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5924. Min Range: -12.5924
Max Act: 12.0924. Min Act: -0.1700
Data Index: 6717420 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5924. Min Range: -12.5924
Max Act: 12.0299. Min Act: -0.1700
Data Index: 5384723 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.8424. Min Act: -0.1700
Data Index: 363321 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.7799. Min Act: -0.1700
Data Index: 3678504 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.7799. Min Act: -0.1700
Data Index: 3361047 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.7174. Min Act: -0.1700
Data Index: 4198030 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.7174. Min Act: -0.1700
Data Index: 6993785 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.5924. Min Act: -0.1700
Data Index: 5141915 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.6549. Min Act: -0.1700
Data Index: 5128868 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.5924. Min Act: -0.1700
Data Index: 8087808 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.5299. Min Act: -0.1700
Data Index: 7640954 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.5299. Min Act: -0.1700
Data Index: 1033319 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.5924. Min Act: -0.1700
Data Index: 2044673 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.5299. Min Act: -0.1700
Data Index: 7841307 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.4674. Min Act: -0.1700
Data Index: 6325237 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.4049. Min Act: -0.1700
Data Index: 7301017 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.3424. Min Act: -0.1700
Data Index: 6127998 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5924. Min Range: -12.5924
Max Act: 11.4049. Min Act: -0.1700
Data Index: 6738626 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19