Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2703 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.3217. Min Act: -0.0001
Data Index: 402004 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.2565. Min Act: -0.0001
Data Index: 203653 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.1836. Min Act: -0.0001
Data Index: 1045522 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.1158. Min Act: -0.0001
Data Index: 42105 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.1277. Min Act: -0.0001
Data Index: 1185065 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.1285. Min Act: -0.0001
Data Index: 1156278 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3217. Min Range: -1.3217
Max Act: 0.9922. Min Act: -0.0001
Data Index: 69674 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.1386. Min Act: -0.0001
Data Index: 69944 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.1624. Min Act: -0.0001
Data Index: 917825 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.1787. Min Act: -0.0001
Data Index: 103609 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.0498. Min Act: -0.0001
Data Index: 668921 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.0725. Min Act: -0.0001
Data Index: 1028549 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.0311. Min Act: -0.0001
Data Index: 265428 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.0563. Min Act: -0.0001
Data Index: 517363 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3217. Min Range: -1.3217
Max Act: 0.9948. Min Act: -0.0001
Data Index: 295727 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.0124. Min Act: -0.0001
Data Index: 635337 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.0678. Min Act: -0.0001
Data Index: 106561 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.0786. Min Act: -0.0001
Data Index: 252745 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3217. Min Range: -1.3217
Max Act: 0.9426. Min Act: -0.0001
Data Index: 1327213 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3217. Min Range: -1.3217
Max Act: 1.0283. Min Act: -0.0001
Data Index: 1082219 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19