Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3289 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.6766. Min Act: -0.0001
Data Index: 492068 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.6137. Min Act: -0.0001
Data Index: 1067101 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5753. Min Act: -0.0001
Data Index: 866831 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5032. Min Act: -0.0001
Data Index: 378741 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5788. Min Act: -0.0001
Data Index: 381861 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5555. Min Act: -0.0001
Data Index: 910158 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5565. Min Act: -0.0001
Data Index: 22508 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5547. Min Act: -0.0001
Data Index: 836568 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5653. Min Act: -0.0001
Data Index: 497154 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.6026. Min Act: -0.0001
Data Index: 35322 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5616. Min Act: -0.0001
Data Index: 853537 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5874. Min Act: -0.0001
Data Index: 1032778 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5544. Min Act: -0.0001
Data Index: 860085 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5498. Min Act: -0.0001
Data Index: 1356973 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5235. Min Act: -0.0001
Data Index: 522916 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5417. Min Act: -0.0001
Data Index: 508408 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5272. Min Act: -0.0001
Data Index: 168783 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5012. Min Act: -0.0001
Data Index: 614211 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5262. Min Act: -0.0001
Data Index: 596423 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6766. Min Range: -0.6766
Max Act: 0.5794. Min Act: -0.0001
Data Index: 482700 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19