Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2687 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2709. Min Range: -1.2709
Max Act: 1.2709. Min Act: -0.0000
Data Index: 596218 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2709. Min Range: -1.2709
Max Act: 1.2433. Min Act: -0.0000
Data Index: 1096758 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.9168. Min Act: -0.0000
Data Index: 172178 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.8060. Min Act: -0.0001
Data Index: 1002078 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.6321. Min Act: -0.0001
Data Index: 1296770 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5909. Min Act: -0.0001
Data Index: 1041564 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5828. Min Act: -0.0001
Data Index: 680307 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5939. Min Act: -0.0001
Data Index: 919472 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5676. Min Act: -0.0000
Data Index: 604034 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5427. Min Act: -0.0001
Data Index: 140479 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5347. Min Act: -0.0001
Data Index: 203924 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5611. Min Act: -0.0001
Data Index: 994694 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5316. Min Act: -0.0001
Data Index: 732364 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5231. Min Act: -0.0001
Data Index: 471721 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5548. Min Act: -0.0001
Data Index: 790752 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5713. Min Act: -0.0001
Data Index: 802030 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5564. Min Act: -0.0001
Data Index: 1097822 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5076. Min Act: -0.0001
Data Index: 730953 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5093. Min Act: -0.0001
Data Index: 674522 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2709. Min Range: -1.2709
Max Act: 0.5331. Min Act: -0.0001
Data Index: 856091 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19