Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 16 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1245. Min Range: -5.1245
Max Act: 5.1245. Min Act: -0.1700
Data Index: 390030 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.8745. Min Act: -0.1700
Data Index: 1123986 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.8120. Min Act: -0.1700
Data Index: 116149 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.8120. Min Act: -0.1700
Data Index: 820659 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.7495. Min Act: -0.1700
Data Index: 788536 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.7182. Min Act: -0.1700
Data Index: 178825 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.7182. Min Act: -0.1700
Data Index: 506340 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.6557. Min Act: -0.1700
Data Index: 236942 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.7182. Min Act: -0.1700
Data Index: 947047 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.6245. Min Act: -0.1700
Data Index: 961270 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.6557. Min Act: -0.1700
Data Index: 383883 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.5932. Min Act: -0.1700
Data Index: 443042 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.6245. Min Act: -0.1700
Data Index: 681619 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.5620. Min Act: -0.1700
Data Index: 239148 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.5620. Min Act: -0.1700
Data Index: 575252 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.5620. Min Act: -0.1700
Data Index: 1069920 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.5620. Min Act: -0.1700
Data Index: 34228 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.5620. Min Act: -0.1700
Data Index: 868577 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.5307. Min Act: -0.1700
Data Index: 1303493 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1245. Min Range: -5.1245
Max Act: 4.5620. Min Act: -0.1700
Data Index: 847367 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19