Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2575 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.6039. Min Act: -0.1700
Data Index: 2127841 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.5102. Min Act: -0.1700
Data Index: 1525574 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.4789. Min Act: -0.1700
Data Index: 207882 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.3852. Min Act: -0.1700
Data Index: 577887 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.3539. Min Act: -0.1700
Data Index: 5131017 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.2602. Min Act: -0.1700
Data Index: 1816830 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.2289. Min Act: -0.1700
Data Index: 2488435 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1977. Min Act: -0.1700
Data Index: 1947350 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1977. Min Act: -0.1686
Data Index: 2320174 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1977. Min Act: -0.1700
Data Index: 4871662 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1664. Min Act: -0.1700
Data Index: 7610985 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1664. Min Act: -0.1700
Data Index: 3822044 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1664. Min Act: -0.1699
Data Index: 7053658 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1664. Min Act: -0.1700
Data Index: 6444362 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1664. Min Act: -0.1700
Data Index: 1473965 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1352. Min Act: -0.1700
Data Index: 3359084 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1352. Min Act: -0.1684
Data Index: 3463042 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1352. Min Act: -0.1700
Data Index: 5821317 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1352. Min Act: -0.1700
Data Index: 209932 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6039. Min Range: -6.6039
Max Act: 6.1352. Min Act: -0.1700
Data Index: 6189716 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19