Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3871 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.7368. Min Act: -0.0001
Data Index: 439887 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.9161. Min Act: -0.0001
Data Index: 867623 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.9166. Min Act: -0.0001
Data Index: 703574 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.7819. Min Act: -0.0001
Data Index: 448303 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.8911. Min Act: -0.0001
Data Index: 420833 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.7637. Min Act: -0.0001
Data Index: 833072 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.6846. Min Act: -0.0001
Data Index: 298890 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.8587. Min Act: -0.0001
Data Index: 726058 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.8307. Min Act: -0.0001
Data Index: 196545 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.7669. Min Act: -0.0001
Data Index: 37521 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.7149. Min Act: -0.0001
Data Index: 960223 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.7633. Min Act: -0.0001
Data Index: 92189 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.7358. Min Act: -0.0002
Data Index: 646922 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.7759. Min Act: -0.0001
Data Index: 477815 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.5924. Min Act: -0.0001
Data Index: 88738 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.6669. Min Act: -0.0001
Data Index: 380808 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.6320. Min Act: -0.0001
Data Index: 1318031 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.6130. Min Act: -0.0001
Data Index: 2816 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.5745. Min Act: -0.0001
Data Index: 259488 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9166. Min Range: -1.9166
Max Act: 1.6991. Min Act: -0.0001
Data Index: 216159 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19