Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4047 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.8097. Min Act: -0.0001
Data Index: 1138772 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.6570. Min Act: -0.0001
Data Index: 904060 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.6405. Min Act: -0.0000
Data Index: 126860 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.5150. Min Act: -0.0001
Data Index: 24481 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.4959. Min Act: -0.0001
Data Index: 915716 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.4760. Min Act: -0.0001
Data Index: 428116 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.1263. Min Act: -0.0001
Data Index: 25651 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.1693. Min Act: -0.0001
Data Index: 808482 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.0261. Min Act: -0.0001
Data Index: 1094965 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.3262. Min Act: -0.0001
Data Index: 1065018 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.1971. Min Act: -0.0001
Data Index: 1018839 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.0868. Min Act: -0.0001
Data Index: 328135 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.0013. Min Act: -0.0000
Data Index: 309281 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.0674. Min Act: -0.0001
Data Index: 114727 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.1773. Min Act: -0.0000
Data Index: 182245 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8097. Min Range: -2.8097
Max Act: 1.8461. Min Act: -0.0001
Data Index: 1293527 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8097. Min Range: -2.8097
Max Act: 1.9858. Min Act: -0.0001
Data Index: 677617 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.0064. Min Act: -0.0001
Data Index: 482749 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8097. Min Range: -2.8097
Max Act: 2.1121. Min Act: -0.0001
Data Index: 491593 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8097. Min Range: -2.8097
Max Act: 1.8920. Min Act: -0.0000
Data Index: 600432 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19