Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6213 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.9363. Min Act: -0.1700
Data Index: 253507 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.8113. Min Act: -0.1700
Data Index: 2585109 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.7801. Min Act: -0.1700
Data Index: 6643810 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.7488. Min Act: -0.1700
Data Index: 1758652 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.6551. Min Act: -0.1700
Data Index: 7391738 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.5613. Min Act: -0.1700
Data Index: 6366863 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.5301. Min Act: -0.1700
Data Index: 1884051 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.4988. Min Act: -0.1700
Data Index: 1495951 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.4676. Min Act: -0.1700
Data Index: 596039 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.4051. Min Act: -0.1700
Data Index: 4846656 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.4051. Min Act: -0.1700
Data Index: 2347568 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.3738. Min Act: -0.1700
Data Index: 3945315 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.3738. Min Act: -0.1700
Data Index: 2750282 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.3113. Min Act: -0.1700
Data Index: 8260004 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.2801. Min Act: -0.1700
Data Index: 1419171 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.3113. Min Act: -0.1700
Data Index: 4785061 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.2801. Min Act: -0.1700
Data Index: 7580373 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.2801. Min Act: -0.1700
Data Index: 2853336 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.2488. Min Act: -0.1700
Data Index: 156128 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9363. Min Range: -6.9363
Max Act: 6.2801. Min Act: -0.1700
Data Index: 4380447 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19