Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2817 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.8255. Min Act: -0.0001
Data Index: 21766 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1374. Min Range: -2.1374
Max Act: 2.0516. Min Act: -0.0001
Data Index: 374387 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1374. Min Range: -2.1374
Max Act: 2.1374. Min Act: -0.0000
Data Index: 430715 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.8988. Min Act: -0.0001
Data Index: 801125 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.9769. Min Act: -0.0000
Data Index: 1240982 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.8360. Min Act: -0.0001
Data Index: 1132957 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.7337. Min Act: -0.0001
Data Index: 240960 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.9075. Min Act: -0.0000
Data Index: 1172406 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.6818. Min Act: -0.0001
Data Index: 145512 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.6634. Min Act: -0.0001
Data Index: 172443 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.7497. Min Act: -0.0001
Data Index: 898221 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.5571. Min Act: -0.0000
Data Index: 551607 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.6882. Min Act: -0.0000
Data Index: 886938 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.6253. Min Act: -0.0001
Data Index: 221155 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.8321. Min Act: -0.0000
Data Index: 122269 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.7544. Min Act: -0.0001
Data Index: 121182 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.7062. Min Act: -0.0001
Data Index: 207339 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.6245. Min Act: -0.0001
Data Index: 391540 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.6097. Min Act: -0.0001
Data Index: 80124 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1374. Min Range: -2.1374
Max Act: 1.6947. Min Act: -0.0001
Data Index: 107951 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19