Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4323 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 17.1615. Min Range: -17.1615
Max Act: 17.1615. Min Act: -0.0001
Data Index: 284618 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.5344. Min Act: -0.0001
Data Index: 1403559 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.4083. Min Act: -0.0001
Data Index: 922332 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.2823. Min Act: -0.0001
Data Index: 352290 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.0293. Min Act: -0.0001
Data Index: 941774 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.1553. Min Act: -0.0001
Data Index: 493234 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.0289. Min Act: -0.0001
Data Index: 198398 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.2809. Min Act: -0.0001
Data Index: 590755 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.1532. Min Act: -0.0001
Data Index: 729057 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.0299. Min Act: -0.0001
Data Index: 483682 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.1615. Min Range: -17.1615
Max Act: 15.9032. Min Act: -0.0001
Data Index: 45826 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.0296. Min Act: -0.0001
Data Index: 798052 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.0290. Min Act: -0.0001
Data Index: 888071 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.1615. Min Range: -17.1615
Max Act: 15.9019. Min Act: -0.0001
Data Index: 780134 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.0276. Min Act: -0.0001
Data Index: 558370 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.0284. Min Act: -0.0001
Data Index: 1155121 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.0272. Min Act: -0.0001
Data Index: 1149204 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.1615. Min Range: -17.1615
Max Act: 16.0231. Min Act: -0.0001
Data Index: 1354156 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.1615. Min Range: -17.1615
Max Act: 15.7772. Min Act: -0.0001
Data Index: 1118162 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.1615. Min Range: -17.1615
Max Act: 15.9040. Min Act: -0.0001
Data Index: 86839 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19