Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.6986. Min Act: -0.1700
Data Index: 7310002 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.4486. Min Act: -0.1700
Data Index: 7230711 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.3861. Min Act: -0.1700
Data Index: 5573854 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.3861. Min Act: -0.1700
Data Index: 7622935 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.2611. Min Act: -0.1700
Data Index: 1563864 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.3236. Min Act: -0.1700
Data Index: 4704378 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1986. Min Act: -0.1700
Data Index: 3888563 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.2611. Min Act: -0.1700
Data Index: 8229706 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1986. Min Act: -0.1700
Data Index: 4499915 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1986. Min Act: -0.1700
Data Index: 3957642 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1986. Min Act: -0.1700
Data Index: 6989758 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.2611. Min Act: -0.1700
Data Index: 3960894 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.2611. Min Act: -0.1700
Data Index: 4810271 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1986. Min Act: -0.1700
Data Index: 8547383 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1361. Min Act: -0.1700
Data Index: 5802740 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1361. Min Act: -0.1700
Data Index: 8291052 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1361. Min Act: -0.1700
Data Index: 1574748 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1361. Min Act: -0.1700
Data Index: 4593270 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.0111. Min Act: -0.1700
Data Index: 6150371 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6986. Min Range: -9.6986
Max Act: 9.1361. Min Act: -0.1700
Data Index: 5131527 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19