Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3185 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5211. Min Range: -2.5211
Max Act: 2.5211. Min Act: -0.0000
Data Index: 1460654 (Python Code)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.9541. Min Act: -0.0001
Data Index: 1021175 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.8289. Min Act: -0.0001
Data Index: 1218723 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.6524. Min Act: -0.0001
Data Index: 499050 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.8543. Min Act: -0.0001
Data Index: 668594 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.5518. Min Act: -0.0001
Data Index: 653431 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.4860. Min Act: -0.0000
Data Index: 715594 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.6539. Min Act: -0.0001
Data Index: 1242449 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.6742. Min Act: -0.0000
Data Index: 368358 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.7269. Min Act: -0.0001
Data Index: 285176 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.4974. Min Act: -0.0001
Data Index: 833492 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.6099. Min Act: -0.0001
Data Index: 936947 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.4750. Min Act: -0.0001
Data Index: 753606 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.5021. Min Act: -0.0000
Data Index: 545669 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.4216. Min Act: -0.0000
Data Index: 1132 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.4963. Min Act: -0.0000
Data Index: 1045613 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.4143. Min Act: -0.0001
Data Index: 719629 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.3423. Min Act: -0.0000
Data Index: 1539696 (Python Code)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.4440. Min Act: -0.0000
Data Index: 664807 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5211. Min Range: -2.5211
Max Act: 1.3632. Min Act: -0.0001
Data Index: 1287375 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19