Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7034. Min Range: -7.7034
Max Act: 7.7034. Min Act: -0.1700
Data Index: 3550846 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7034. Min Range: -7.7034
Max Act: 7.4221. Min Act: -0.1700
Data Index: 5976814 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7034. Min Range: -7.7034
Max Act: 7.1409. Min Act: -0.1700
Data Index: 6198401 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7034. Min Range: -7.7034
Max Act: 7.1409. Min Act: -0.1700
Data Index: 97828 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7034. Min Range: -7.7034
Max Act: 7.0784. Min Act: -0.1700
Data Index: 4071772 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7034. Min Range: -7.7034
Max Act: 7.0784. Min Act: -0.1700
Data Index: 7184714 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7034. Min Range: -7.7034
Max Act: 7.0784. Min Act: -0.1700
Data Index: 4460562 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7034. Min Range: -7.7034
Max Act: 7.0784. Min Act: -0.1700
Data Index: 2055789 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7034. Min Range: -7.7034
Max Act: 7.0471. Min Act: -0.1700
Data Index: 5670592 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9846. Min Act: -0.1700
Data Index: 3533039 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9846. Min Act: -0.1700
Data Index: 8821296 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9846. Min Act: -0.1700
Data Index: 1773971 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9846. Min Act: -0.1700
Data Index: 8530394 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9846. Min Act: -0.1700
Data Index: 2046872 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9846. Min Act: -0.1700
Data Index: 7299788 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9846. Min Act: -0.1700
Data Index: 5143345 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9221. Min Act: -0.1700
Data Index: 3132906 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9221. Min Act: -0.1700
Data Index: 7374422 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.9221. Min Act: -0.1700
Data Index: 4557389 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7034. Min Range: -7.7034
Max Act: 6.8909. Min Act: -0.1700
Data Index: 7005706 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19