Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3048 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.1032. Min Act: -0.0004
Data Index: 743774 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0849. Min Act: -0.0004
Data Index: 1621252 (Python Code)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0966. Min Act: -0.0004
Data Index: 947921 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.1008. Min Act: -0.0004
Data Index: 660911 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0951. Min Act: -0.0004
Data Index: 615794 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0947. Min Act: -0.0004
Data Index: 747555 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0978. Min Act: -0.0004
Data Index: 936957 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.1000. Min Act: -0.0004
Data Index: 1408052 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0961. Min Act: -0.0004
Data Index: 992552 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0920. Min Act: -0.0004
Data Index: 310734 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.1063. Min Act: -0.0004
Data Index: 633798 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.1021. Min Act: -0.0004
Data Index: 8833 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0909. Min Act: -0.0004
Data Index: 238997 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.1097. Min Act: -0.0004
Data Index: 222390 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0907. Min Act: -0.0004
Data Index: 940368 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0745. Min Act: -0.0004
Data Index: 569112 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0803. Min Act: -0.0004
Data Index: 1134450 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0967. Min Act: -0.0004
Data Index: 1250539 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0939. Min Act: -0.0004
Data Index: 336271 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1097. Min Range: -0.1097
Max Act: 0.0967. Min Act: -0.0004
Data Index: 205540 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19