Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2732 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.7718. Min Act: -0.0001
Data Index: 387720 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.8548. Min Act: -0.0001
Data Index: 454692 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.7644. Min Act: -0.0001
Data Index: 717359 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.4271. Min Act: -0.0001
Data Index: 1197806 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.4850. Min Act: -0.0001
Data Index: 332068 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.3860. Min Act: -0.0001
Data Index: 563991 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.5043. Min Act: -0.0001
Data Index: 17936 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.5228. Min Act: -0.0001
Data Index: 546131 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.5516. Min Act: -0.0001
Data Index: 890025 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.2208. Min Act: -0.0001
Data Index: 40227 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.4602. Min Act: -0.0001
Data Index: 953240 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.6103. Min Act: -0.0001
Data Index: 881666 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.3681. Min Act: -0.0001
Data Index: 1052504 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.3169. Min Act: -0.0001
Data Index: 885191 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.5160. Min Act: -0.0001
Data Index: 165395 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.5536. Min Act: -0.0001
Data Index: 219734 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.4519. Min Act: -0.0001
Data Index: 705716 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.5781. Min Act: -0.0001
Data Index: 451170 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.4043. Min Act: -0.0001
Data Index: 303187 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8548. Min Range: -1.8548
Max Act: 1.4329. Min Act: -0.0001
Data Index: 801403 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19