Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5093 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2034. Min Range: -2.2034
Max Act: 2.2034. Min Act: -0.0002
Data Index: 802923 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.9152. Min Act: -0.0002
Data Index: 1087505 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.7851. Min Act: -0.0002
Data Index: 98687 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.4350. Min Act: -0.0002
Data Index: 818607 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.6355. Min Act: -0.0002
Data Index: 850386 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.5941. Min Act: -0.0002
Data Index: 788265 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.6407. Min Act: -0.0002
Data Index: 354332 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.5298. Min Act: -0.0002
Data Index: 903276 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.6510. Min Act: -0.0002
Data Index: 411997 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.5657. Min Act: -0.0002
Data Index: 71618 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.4883. Min Act: -0.0002
Data Index: 1239565 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.4833. Min Act: -0.0002
Data Index: 18394 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.4925. Min Act: -0.0002
Data Index: 921443 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.2210. Min Act: -0.0002
Data Index: 1325563 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.4607. Min Act: -0.0002
Data Index: 420206 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.4279. Min Act: -0.0002
Data Index: 402464 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.3522. Min Act: -0.0002
Data Index: 426870 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.6776. Min Act: -0.0002
Data Index: 125950 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.3966. Min Act: -0.0002
Data Index: 674447 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2034. Min Range: -2.2034
Max Act: 1.2888. Min Act: -0.0002
Data Index: 660854 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19