Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1311 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.3483. Min Act: -0.0001
Data Index: 1007118 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.4830. Min Act: -0.0001
Data Index: 173480 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.3697. Min Act: -0.0001
Data Index: 162106 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.2421. Min Act: -0.0001
Data Index: 817261 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.0880. Min Act: -0.0001
Data Index: 544839 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.2687. Min Act: -0.0001
Data Index: 1255894 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.1273. Min Act: -0.0001
Data Index: 287978 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.2190. Min Act: -0.0001
Data Index: 1040610 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.2134. Min Act: -0.0001
Data Index: 823780 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4830. Min Range: -2.4830
Max Act: 1.9506. Min Act: -0.0001
Data Index: 947234 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.0927. Min Act: -0.0001
Data Index: 1334862 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4830. Min Range: -2.4830
Max Act: 1.9858. Min Act: -0.0001
Data Index: 1068806 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4830. Min Range: -2.4830
Max Act: 1.9778. Min Act: -0.0001
Data Index: 698925 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4830. Min Range: -2.4830
Max Act: 1.8617. Min Act: -0.0001
Data Index: 504685 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4830. Min Range: -2.4830
Max Act: 1.9403. Min Act: -0.0001
Data Index: 903648 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4830. Min Range: -2.4830
Max Act: 2.0381. Min Act: -0.0001
Data Index: 842135 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4830. Min Range: -2.4830
Max Act: 1.9851. Min Act: -0.0001
Data Index: 1335539 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4830. Min Range: -2.4830
Max Act: 1.9815. Min Act: -0.0001
Data Index: 1004017 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4830. Min Range: -2.4830
Max Act: 1.6512. Min Act: -0.0001
Data Index: 225105 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4830. Min Range: -2.4830
Max Act: 1.6623. Min Act: -0.0001
Data Index: 1147325 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19