Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4100 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2791. Min Range: -2.2791
Max Act: 2.2791. Min Act: -0.0002
Data Index: 1006848 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2791. Min Range: -2.2791
Max Act: 2.2019. Min Act: -0.0001
Data Index: 603934 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2791. Min Range: -2.2791
Max Act: 2.1716. Min Act: -0.0001
Data Index: 456086 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2791. Min Range: -2.2791
Max Act: 2.0198. Min Act: -0.0001
Data Index: 672492 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2791. Min Range: -2.2791
Max Act: 2.1970. Min Act: -0.0001
Data Index: 164326 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2791. Min Range: -2.2791
Max Act: 2.0976. Min Act: -0.0001
Data Index: 1208816 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.9903. Min Act: -0.0001
Data Index: 647034 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.9768. Min Act: -0.0002
Data Index: 1022601 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2791. Min Range: -2.2791
Max Act: 2.0660. Min Act: -0.0002
Data Index: 1181768 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2791. Min Range: -2.2791
Max Act: 2.0548. Min Act: -0.0001
Data Index: 1071115 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.8627. Min Act: -0.0001
Data Index: 46663 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.9399. Min Act: -0.0002
Data Index: 1008733 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.9343. Min Act: -0.0001
Data Index: 286823 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.9256. Min Act: -0.0001
Data Index: 889771 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.9905. Min Act: -0.0001
Data Index: 404729 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2791. Min Range: -2.2791
Max Act: 2.0614. Min Act: -0.0001
Data Index: 578058 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.9558. Min Act: -0.0002
Data Index: 773355 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.9210. Min Act: -0.0001
Data Index: 1099645 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.8171. Min Act: -0.0002
Data Index: 946930 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2791. Min Range: -2.2791
Max Act: 1.8085. Min Act: -0.0001
Data Index: 1226805 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19