Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3450 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2020. Min Range: -2.2020
Max Act: 2.2020. Min Act: -0.0000
Data Index: 173462 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.9940. Min Act: -0.0000
Data Index: 577781 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.9354. Min Act: -0.0000
Data Index: 864597 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.8916. Min Act: -0.0000
Data Index: 371629 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.8749. Min Act: -0.0000
Data Index: 514299 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.8220. Min Act: -0.0000
Data Index: 370113 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.7673. Min Act: -0.0000
Data Index: 395159 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6336. Min Act: -0.0000
Data Index: 613615 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6170. Min Act: -0.0000
Data Index: 728649 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6971. Min Act: -0.0000
Data Index: 624615 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.5911. Min Act: -0.0000
Data Index: 806694 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6825. Min Act: -0.0000
Data Index: 885586 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.7718. Min Act: -0.0000
Data Index: 1590328 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6579. Min Act: -0.0000
Data Index: 1603407 (Python Code)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6459. Min Act: -0.0000
Data Index: 797577 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6379. Min Act: -0.0000
Data Index: 55637 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6360. Min Act: -0.0000
Data Index: 99569 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6188. Min Act: -0.0000
Data Index: 966215 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.6111. Min Act: -0.0000
Data Index: 23577 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2020. Min Range: -2.2020
Max Act: 1.5606. Min Act: -0.0000
Data Index: 636889 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19