Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2160 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.1665. Min Range: -2.1665
Max Act: 2.1665. Min Act: -0.0001
Data Index: 186792 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1665. Min Range: -2.1665
Max Act: 2.0883. Min Act: -0.0001
Data Index: 1051305 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1665. Min Range: -2.1665
Max Act: 2.0235. Min Act: -0.0001
Data Index: 1171551 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.9178. Min Act: -0.0001
Data Index: 682973 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.9017. Min Act: -0.0001
Data Index: 570469 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.8905. Min Act: -0.0001
Data Index: 326674 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.8086. Min Act: -0.0001
Data Index: 874473 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.8715. Min Act: -0.0001
Data Index: 712657 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.5361. Min Act: -0.0001
Data Index: 335242 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.8599. Min Act: -0.0001
Data Index: 31490 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.8635. Min Act: -0.0001
Data Index: 654106 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.7888. Min Act: -0.0001
Data Index: 1122628 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.6427. Min Act: -0.0001
Data Index: 1045523 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.7176. Min Act: -0.0001
Data Index: 942531 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.7571. Min Act: -0.0001
Data Index: 520398 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.8025. Min Act: -0.0001
Data Index: 747765 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.7266. Min Act: -0.0001
Data Index: 242964 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.7171. Min Act: -0.0001
Data Index: 909141 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.7615. Min Act: -0.0001
Data Index: 1265400 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1665. Min Range: -2.1665
Max Act: 1.7092. Min Act: -0.0001
Data Index: 906981 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19