Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3801 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.4369. Min Range: -3.4369
Max Act: 3.4369. Min Act: -0.0001
Data Index: 760947 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.6345. Min Act: -0.0001
Data Index: 1124078 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.6070. Min Act: -0.0001
Data Index: 1316026 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.4877. Min Act: -0.0001
Data Index: 622819 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.7194. Min Act: -0.0001
Data Index: 1117131 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.2073. Min Act: -0.0001
Data Index: 94658 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.2231. Min Act: -0.0001
Data Index: 29124 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.3175. Min Act: -0.0001
Data Index: 1247231 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.2454. Min Act: -0.0001
Data Index: 637947 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.3971. Min Act: -0.0001
Data Index: 479993 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.1587. Min Act: -0.0001
Data Index: 877658 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4369. Min Range: -3.4369
Max Act: 1.9611. Min Act: -0.0001
Data Index: 1357551 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.2794. Min Act: -0.0001
Data Index: 1196729 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.3874. Min Act: -0.0001
Data Index: 85844 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.3242. Min Act: -0.0001
Data Index: 1028339 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.2223. Min Act: -0.0001
Data Index: 1263642 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.2168. Min Act: -0.0001
Data Index: 1282050 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.3049. Min Act: -0.0001
Data Index: 424000 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.1696. Min Act: -0.0001
Data Index: 971767 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4369. Min Range: -3.4369
Max Act: 2.0488. Min Act: -0.0001
Data Index: 79240 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19