Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4214 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.5628. Min Act: -0.0001
Data Index: 594628 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5628. Min Range: -3.5628
Max Act: 2.7076. Min Act: -0.0001
Data Index: 39949 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5628. Min Range: -3.5628
Max Act: 2.0603. Min Act: -0.0001
Data Index: 1161008 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5628. Min Range: -3.5628
Max Act: 2.1130. Min Act: -0.0001
Data Index: 1240694 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.9206. Min Act: -0.0001
Data Index: 795527 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5628. Min Range: -3.5628
Max Act: 2.0372. Min Act: -0.0001
Data Index: 659589 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.8215. Min Act: -0.0001
Data Index: 326168 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5628. Min Range: -3.5628
Max Act: 2.0014. Min Act: -0.0001
Data Index: 837519 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.8600. Min Act: -0.0001
Data Index: 1198581 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.8605. Min Act: -0.0000
Data Index: 633662 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.7760. Min Act: -0.0001
Data Index: 1171239 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.8394. Min Act: -0.0001
Data Index: 910433 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.9991. Min Act: -0.0001
Data Index: 540950 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.7829. Min Act: -0.0001
Data Index: 786903 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.6246. Min Act: -0.0001
Data Index: 60958 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.8745. Min Act: -0.0001
Data Index: 835653 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.6469. Min Act: -0.0001
Data Index: 1254959 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.7398. Min Act: -0.0001
Data Index: 881822 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.6335. Min Act: -0.0001
Data Index: 526103 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5628. Min Range: -3.5628
Max Act: 1.6085. Min Act: -0.0001
Data Index: 522664 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19