Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1538 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.0483. Min Range: -1.0483
Max Act: 1.0483. Min Act: -0.0002
Data Index: 913376 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0483. Min Range: -1.0483
Max Act: 1.0434. Min Act: -0.0002
Data Index: 233657 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0483. Min Range: -1.0483
Max Act: 1.0311. Min Act: -0.0002
Data Index: 1475156 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0483. Min Range: -1.0483
Max Act: 1.0035. Min Act: -0.0002
Data Index: 719663 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9912. Min Act: -0.0002
Data Index: 44948 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9840. Min Act: -0.0002
Data Index: 1667313 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0483. Min Range: -1.0483
Max Act: 1.0090. Min Act: -0.0002
Data Index: 615319 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0483. Min Range: -1.0483
Max Act: 1.0163. Min Act: -0.0002
Data Index: 232745 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0483. Min Range: -1.0483
Max Act: 1.0349. Min Act: -0.0002
Data Index: 1607004 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9735. Min Act: -0.0002
Data Index: 993613 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0483. Min Range: -1.0483
Max Act: 1.0176. Min Act: -0.0002
Data Index: 1610800 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0483. Min Range: -1.0483
Max Act: 1.0033. Min Act: -0.0002
Data Index: 227523 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9770. Min Act: -0.0002
Data Index: 1155413 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9746. Min Act: -0.0002
Data Index: 1606997 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9456. Min Act: -0.0002
Data Index: 835902 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9553. Min Act: -0.0002
Data Index: 1995486 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9523. Min Act: -0.0002
Data Index: 634177 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9516. Min Act: -0.0002
Data Index: 306509 (The Pile)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9210. Min Act: -0.0002
Data Index: 1093103 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0483. Min Range: -1.0483
Max Act: 0.9464. Min Act: -0.0002
Data Index: 723749 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19