Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3855 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0890. Min Act: -0.0002
Data Index: 1232108 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.1127. Min Act: -0.0001
Data Index: 828563 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.1148. Min Act: -0.0001
Data Index: 322551 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.1678. Min Act: -0.0001
Data Index: 755585 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0881. Min Act: -0.0002
Data Index: 1311471 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0602. Min Act: -0.0001
Data Index: 454094 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0572. Min Act: -0.0002
Data Index: 55428 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1678. Min Range: -1.1678
Max Act: 0.9462. Min Act: -0.0001
Data Index: 122810 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0862. Min Act: -0.0002
Data Index: 866671 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0755. Min Act: -0.0002
Data Index: 336324 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1678. Min Range: -1.1678
Max Act: 0.9862. Min Act: -0.0001
Data Index: 760011 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0192. Min Act: -0.0002
Data Index: 807860 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0068. Min Act: -0.0002
Data Index: 1335753 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0136. Min Act: -0.0002
Data Index: 1338148 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0005. Min Act: -0.0001
Data Index: 850734 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1678. Min Range: -1.1678
Max Act: 1.0228. Min Act: -0.0001
Data Index: 271368 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1678. Min Range: -1.1678
Max Act: 0.9933. Min Act: -0.0001
Data Index: 877727 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1678. Min Range: -1.1678
Max Act: 0.9913. Min Act: -0.0001
Data Index: 1211700 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1678. Min Range: -1.1678
Max Act: 0.9895. Min Act: -0.0001
Data Index: 592460 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1678. Min Range: -1.1678
Max Act: 0.9884. Min Act: -0.0001
Data Index: 822333 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19