Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2453. Min Range: -6.2453
Max Act: 6.2453. Min Act: -0.1700
Data Index: 4468139 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2453. Min Range: -6.2453
Max Act: 6.0578. Min Act: -0.1700
Data Index: 3577550 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2453. Min Range: -6.2453
Max Act: 6.0578. Min Act: -0.1700
Data Index: 270529 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.9015. Min Act: -0.1700
Data Index: 5081516 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.9015. Min Act: -0.1700
Data Index: 5157561 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.8703. Min Act: -0.1700
Data Index: 6130596 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.8703. Min Act: -0.1700
Data Index: 4837971 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.8390. Min Act: -0.1700
Data Index: 1418430 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.8078. Min Act: -0.1700
Data Index: 3495293 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.8078. Min Act: -0.1700
Data Index: 554768 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.8078. Min Act: -0.1700
Data Index: 7871967 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.7765. Min Act: -0.1700
Data Index: 90650 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.8078. Min Act: -0.1700
Data Index: 3242158 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.7765. Min Act: -0.1700
Data Index: 487692 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.7765. Min Act: -0.1700
Data Index: 4445090 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.7453. Min Act: -0.1700
Data Index: 3039720 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.6828. Min Act: -0.1700
Data Index: 7869414 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.6828. Min Act: -0.1700
Data Index: 287461 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.6828. Min Act: -0.1700
Data Index: 4834424 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2453. Min Range: -6.2453
Max Act: 5.6828. Min Act: -0.1700
Data Index: 2299199 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19