Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2876 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.6175. Min Act: -0.0001
Data Index: 72046 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.6447. Min Act: -0.0001
Data Index: 1046229 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.6178. Min Act: -0.0001
Data Index: 380149 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.4770. Min Act: -0.0001
Data Index: 1039054 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.5143. Min Act: -0.0001
Data Index: 506931 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.4535. Min Act: -0.0001
Data Index: 1289450 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.5058. Min Act: -0.0001
Data Index: 1236683 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.4784. Min Act: -0.0001
Data Index: 410945 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.5608. Min Act: -0.0001
Data Index: 346556 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.4192. Min Act: -0.0001
Data Index: 307114 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.5195. Min Act: -0.0001
Data Index: 852437 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.4372. Min Act: -0.0001
Data Index: 226474 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.4298. Min Act: -0.0001
Data Index: 129580 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.4238. Min Act: -0.0001
Data Index: 1090091 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.3657. Min Act: -0.0001
Data Index: 635537 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.3854. Min Act: -0.0001
Data Index: 1108225 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.4986. Min Act: -0.0001
Data Index: 749450 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.4295. Min Act: -0.0001
Data Index: 1147982 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.3819. Min Act: -0.0001
Data Index: 1188327 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6447. Min Range: -1.6447
Max Act: 1.3838. Min Act: -0.0001
Data Index: 906729 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19