Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2688 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.7990. Min Act: -0.0001
Data Index: 1294067 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.7677. Min Act: -0.0001
Data Index: 867731 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.6346. Min Act: -0.0001
Data Index: 1348792 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.7020. Min Act: -0.0001
Data Index: 1314883 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.5927. Min Act: -0.0001
Data Index: 870851 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.3638. Min Act: -0.0001
Data Index: 388051 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.6013. Min Act: -0.0001
Data Index: 1122065 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.2267. Min Act: -0.0001
Data Index: 1132106 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.4187. Min Act: -0.0001
Data Index: 1183167 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.6815. Min Act: -0.0001
Data Index: 1126037 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.5405. Min Act: -0.0001
Data Index: 936994 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.3918. Min Act: -0.0001
Data Index: 749503 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.5865. Min Act: -0.0001
Data Index: 766724 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.4496. Min Act: -0.0001
Data Index: 294692 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.2768. Min Act: -0.0001
Data Index: 512969 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.5775. Min Act: -0.0001
Data Index: 355792 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.3457. Min Act: -0.0001
Data Index: 1258708 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.2320. Min Act: -0.0001
Data Index: 204555 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.2050. Min Act: -0.0001
Data Index: 642143 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7990. Min Range: -2.7990
Max Act: 2.2017. Min Act: -0.0001
Data Index: 638838 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19