Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 37 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.8064. Min Act: -0.1700
Data Index: 911341 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.7905. Min Act: -0.1700
Data Index: 187577 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.8223. Min Act: -0.1700
Data Index: 752973 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.7267. Min Act: -0.1700
Data Index: 65954 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6787. Min Act: -0.1700
Data Index: 27625 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6626. Min Act: -0.1700
Data Index: 7278 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6626. Min Act: -0.1700
Data Index: 1228324 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6787. Min Act: -0.1700
Data Index: 751497 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6466. Min Act: -0.1700
Data Index: 959027 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6626. Min Act: -0.1700
Data Index: 700074 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6626. Min Act: -0.1700
Data Index: 425071 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6466. Min Act: -0.1700
Data Index: 717636 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6466. Min Act: -0.1700
Data Index: 40040 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6466. Min Act: -0.1700
Data Index: 877191 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6145. Min Act: -0.1700
Data Index: 877409 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.5823. Min Act: -0.1700
Data Index: 1169708 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6145. Min Act: -0.1700
Data Index: 556648 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.5984. Min Act: -0.1700
Data Index: 361667 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6145. Min Act: -0.1700
Data Index: 498747 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8223. Min Range: -2.8223
Max Act: 2.6305. Min Act: -0.1700
Data Index: 1065621 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19