Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5916 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.4991. Min Act: -0.0002
Data Index: 476770 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.3975. Min Act: -0.0002
Data Index: 419712 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.4278. Min Act: -0.0002
Data Index: 193885 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.3400. Min Act: -0.0002
Data Index: 1267758 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.3850. Min Act: -0.0002
Data Index: 596459 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.3727. Min Act: -0.0002
Data Index: 178857 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.2559. Min Act: -0.0002
Data Index: 706274 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.2966. Min Act: -0.0002
Data Index: 481982 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.3168. Min Act: -0.0002
Data Index: 386562 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.2465. Min Act: -0.0002
Data Index: 64527 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.2982. Min Act: -0.0002
Data Index: 531909 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.2874. Min Act: -0.0002
Data Index: 1307137 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.2060. Min Act: -0.0002
Data Index: 788931 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.2010. Min Act: -0.0002
Data Index: 117849 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.2532. Min Act: -0.0002
Data Index: 1282615 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.2560. Min Act: -0.0002
Data Index: 420402 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.0459. Min Act: -0.0002
Data Index: 1027939 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.1802. Min Act: -0.0002
Data Index: 763215 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.1729. Min Act: -0.0002
Data Index: 862094 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 2.4991. Min Range: -2.4991
Max Act: 2.1887. Min Act: -0.0002
Data Index: 203208 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full textTruncated
Full Text #19