Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3771 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.7703. Min Act: -0.0001
Data Index: 413530 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.4747. Min Act: -0.0001
Data Index: 336114 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3883. Min Act: -0.0001
Data Index: 188647 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.2855. Min Act: -0.0001
Data Index: 301766 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3300. Min Act: -0.0001
Data Index: 107846 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3202. Min Act: -0.0001
Data Index: 38851 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3299. Min Act: -0.0001
Data Index: 952427 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3885. Min Act: -0.0001
Data Index: 949102 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.4694. Min Act: -0.0001
Data Index: 1318007 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.2216. Min Act: -0.0001
Data Index: 851664 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.2413. Min Act: -0.0001
Data Index: 630884 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3571. Min Act: -0.0001
Data Index: 436609 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.1737. Min Act: -0.0001
Data Index: 1298013 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.4157. Min Act: -0.0001
Data Index: 520846 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3141. Min Act: -0.0001
Data Index: 1116694 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3243. Min Act: -0.0001
Data Index: 83326 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.2469. Min Act: -0.0001
Data Index: 337353 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.2489. Min Act: -0.0001
Data Index: 734328 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3039. Min Act: -0.0001
Data Index: 1233690 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7703. Min Range: -1.7703
Max Act: 1.3678. Min Act: -0.0001
Data Index: 1206846 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19