Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2212. Min Range: -8.2212
Max Act: 8.2212. Min Act: -0.1700
Data Index: 5726367 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.9712. Min Act: -0.1700
Data Index: 7435869 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.9712. Min Act: -0.1700
Data Index: 4610170 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.9087. Min Act: -0.1700
Data Index: 7044017 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.8462. Min Act: -0.1700
Data Index: 5079855 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.8462. Min Act: -0.1700
Data Index: 5888917 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.7837. Min Act: -0.1700
Data Index: 1201143 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.7837. Min Act: -0.1700
Data Index: 8697228 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.7212. Min Act: -0.1700
Data Index: 2311436 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.7212. Min Act: -0.1700
Data Index: 5569986 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.6587. Min Act: -0.1700
Data Index: 1674804 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.7212. Min Act: -0.1700
Data Index: 5943207 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.7212. Min Act: -0.1700
Data Index: 1409435 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.6587. Min Act: -0.1700
Data Index: 5631014 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.7212. Min Act: -0.1700
Data Index: 16959 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.5337. Min Act: -0.1700
Data Index: 8020225 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.5337. Min Act: -0.1700
Data Index: 8790667 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.5337. Min Act: -0.1700
Data Index: 7661715 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.5337. Min Act: -0.1700
Data Index: 953952 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2212. Min Range: -8.2212
Max Act: 7.5337. Min Act: -0.1700
Data Index: 7364570 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19