Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 991 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5028. Min Range: -2.5028
Max Act: 2.5028. Min Act: -0.0001
Data Index: 489614 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.8820. Min Act: -0.0001
Data Index: 948722 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.8087. Min Act: -0.0000
Data Index: 1479283 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.4633. Min Act: -0.0001
Data Index: 49175 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.7606. Min Act: -0.0000
Data Index: 1380447 (Python Code)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.7322. Min Act: -0.0001
Data Index: 1264574 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.7077. Min Act: -0.0001
Data Index: 1068632 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.8055. Min Act: -0.0001
Data Index: 182301 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.6060. Min Act: -0.0001
Data Index: 1102627 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.7618. Min Act: -0.0001
Data Index: 1006824 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.6489. Min Act: -0.0001
Data Index: 1159423 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.6197. Min Act: -0.0001
Data Index: 958334 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.6022. Min Act: -0.0001
Data Index: 85300 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.5045. Min Act: -0.0001
Data Index: 506480 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.6814. Min Act: -0.0001
Data Index: 1049011 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.5779. Min Act: -0.0001
Data Index: 140933 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.5159. Min Act: -0.0001
Data Index: 595788 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.5261. Min Act: -0.0001
Data Index: 320429 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.6490. Min Act: -0.0001
Data Index: 1278069 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5028. Min Range: -2.5028
Max Act: 1.5547. Min Act: -0.0001
Data Index: 911103 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19