Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3591 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0007. Min Range: -2.0007
Max Act: 2.0007. Min Act: -0.0002
Data Index: 431506 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.7635. Min Act: -0.0002
Data Index: 596469 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.7549. Min Act: -0.0002
Data Index: 1044945 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.6879. Min Act: -0.0002
Data Index: 569935 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.6068. Min Act: -0.0002
Data Index: 439633 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.4750. Min Act: -0.0002
Data Index: 773912 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.8673. Min Act: -0.0002
Data Index: 1027153 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.5574. Min Act: -0.0002
Data Index: 1211834 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.5150. Min Act: -0.0002
Data Index: 846140 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.6682. Min Act: -0.0002
Data Index: 1183163 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.5522. Min Act: -0.0002
Data Index: 1563336 (Python Code)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.7207. Min Act: -0.0002
Data Index: 1322539 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.6806. Min Act: -0.0002
Data Index: 297397 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.6157. Min Act: -0.0002
Data Index: 301600 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.3412. Min Act: -0.0002
Data Index: 829162 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.4304. Min Act: -0.0002
Data Index: 762197 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.5206. Min Act: -0.0003
Data Index: 1070167 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.5707. Min Act: -0.0002
Data Index: 234905 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.4493. Min Act: -0.0002
Data Index: 1574967 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0007. Min Range: -2.0007
Max Act: 1.4838. Min Act: -0.0002
Data Index: 6322 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19