Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 202 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.6719. Min Act: -0.0001
Data Index: 223016 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4884. Min Act: -0.0001
Data Index: 428451 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.6621. Min Act: -0.0001
Data Index: 584205 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.7118. Min Act: -0.0001
Data Index: 318300 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.5071. Min Act: -0.0001
Data Index: 807073 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4853. Min Act: -0.0001
Data Index: 393054 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4870. Min Act: -0.0001
Data Index: 716645 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4588. Min Act: -0.0001
Data Index: 952285 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4275. Min Act: -0.0001
Data Index: 308908 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.5012. Min Act: -0.0001
Data Index: 1122747 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4204. Min Act: -0.0001
Data Index: 921322 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4859. Min Act: -0.0001
Data Index: 639068 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.5721. Min Act: -0.0001
Data Index: 643063 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.3048. Min Act: -0.0001
Data Index: 55968 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.3553. Min Act: -0.0001
Data Index: 1247143 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.5170. Min Act: -0.0001
Data Index: 750304 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4153. Min Act: -0.0001
Data Index: 1499654 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4016. Min Act: -0.0001
Data Index: 326970 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.4891. Min Act: -0.0001
Data Index: 1346493 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7118. Min Range: -1.7118
Max Act: 1.5968. Min Act: -0.0001
Data Index: 1414247 (Python Code)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19