Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3044 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.7578. Min Act: -0.0001
Data Index: 390402 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.6989. Min Act: -0.0001
Data Index: 530188 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.5365. Min Act: -0.0001
Data Index: 1046121 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.5309. Min Act: -0.0001
Data Index: 1285676 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4898. Min Act: -0.0001
Data Index: 385824 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.5016. Min Act: -0.0001
Data Index: 1026534 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4645. Min Act: -0.0001
Data Index: 421724 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4739. Min Act: -0.0001
Data Index: 748850 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4559. Min Act: -0.0001
Data Index: 161046 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4901. Min Act: -0.0001
Data Index: 1249439 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4589. Min Act: -0.0001
Data Index: 208014 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4572. Min Act: -0.0001
Data Index: 326541 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4294. Min Act: -0.0001
Data Index: 528840 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4363. Min Act: -0.0001
Data Index: 9232 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4651. Min Act: -0.0001
Data Index: 1127587 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.3987. Min Act: -0.0001
Data Index: 347132 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4207. Min Act: -0.0001
Data Index: 433482 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.3908. Min Act: -0.0001
Data Index: 1054048 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.4010. Min Act: -0.0001
Data Index: 688483 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7578. Min Range: -0.7578
Max Act: 0.3871. Min Act: -0.0001
Data Index: 300226 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19