Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3417 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.8382. Min Range: -3.8382
Max Act: 3.8382. Min Act: -0.0001
Data Index: 4368 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8382. Min Range: -3.8382
Max Act: 3.1501. Min Act: -0.0001
Data Index: 546840 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.7588. Min Act: -0.0001
Data Index: 421328 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.8299. Min Act: -0.0001
Data Index: 1290674 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.6146. Min Act: -0.0001
Data Index: 834728 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.6823. Min Act: -0.0001
Data Index: 873359 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.4930. Min Act: -0.0001
Data Index: 540782 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.6186. Min Act: -0.0001
Data Index: 165475 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.7479. Min Act: -0.0001
Data Index: 300794 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.4686. Min Act: -0.0001
Data Index: 15374 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.4164. Min Act: -0.0001
Data Index: 1135351 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.5169. Min Act: -0.0001
Data Index: 1210815 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.4077. Min Act: -0.0001
Data Index: 1260050 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.5005. Min Act: -0.0001
Data Index: 886572 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.4035. Min Act: -0.0001
Data Index: 714776 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.6307. Min Act: -0.0001
Data Index: 21685 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.4087. Min Act: -0.0001
Data Index: 492231 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.5118. Min Act: -0.0001
Data Index: 1159885 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.4995. Min Act: -0.0001
Data Index: 25138 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8382. Min Range: -3.8382
Max Act: 2.4765. Min Act: -0.0001
Data Index: 927949 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19