Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1320 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.1553. Min Range: -2.1553
Max Act: 2.1553. Min Act: -0.0001
Data Index: 1615350 (Python Code)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.9281. Min Act: -0.0001
Data Index: 1114789 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.9541. Min Act: -0.0001
Data Index: 711564 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.5511. Min Act: -0.0001
Data Index: 320852 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.7940. Min Act: -0.0001
Data Index: 323642 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.6717. Min Act: -0.0002
Data Index: 776535 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.5545. Min Act: -0.0002
Data Index: 89472 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.7400. Min Act: -0.0001
Data Index: 1030024 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.7357. Min Act: -0.0002
Data Index: 197520 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.7383. Min Act: -0.0001
Data Index: 1044598 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.6752. Min Act: -0.0001
Data Index: 67786 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.6362. Min Act: -0.0001
Data Index: 1591418 (Python Code)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.6149. Min Act: -0.0001
Data Index: 250296 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.6040. Min Act: -0.0001
Data Index: 554589 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.6706. Min Act: -0.0001
Data Index: 1296471 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.6214. Min Act: -0.0002
Data Index: 383744 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.6639. Min Act: -0.0001
Data Index: 542522 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.6766. Min Act: -0.0001
Data Index: 854049 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.4865. Min Act: -0.0001
Data Index: 859623 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1553. Min Range: -2.1553
Max Act: 1.5821. Min Act: -0.0001
Data Index: 791297 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19