Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3619 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 6.5193. Min Range: -6.5193
Max Act: 6.5193. Min Act: -0.0001
Data Index: 313921 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.5384. Min Act: -0.0001
Data Index: 109049 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.4084. Min Act: -0.0001
Data Index: 918683 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.4180. Min Act: -0.0001
Data Index: 620007 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.2115. Min Act: -0.0001
Data Index: 1116046 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.6840. Min Act: -0.0001
Data Index: 652954 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.3215. Min Act: -0.0001
Data Index: 1036651 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.8590. Min Act: -0.0001
Data Index: 571790 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5193. Min Range: -6.5193
Max Act: 4.8896. Min Act: -0.0001
Data Index: 1067924 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.2268. Min Act: -0.0001
Data Index: 1237058 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.0220. Min Act: -0.0001
Data Index: 1145092 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5193. Min Range: -6.5193
Max Act: 4.9771. Min Act: -0.0001
Data Index: 474796 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.2731. Min Act: -0.0001
Data Index: 364087 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.2616. Min Act: -0.0001
Data Index: 116162 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5193. Min Range: -6.5193
Max Act: 4.8976. Min Act: -0.0001
Data Index: 243281 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.2347. Min Act: -0.0001
Data Index: 164098 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5193. Min Range: -6.5193
Max Act: 4.7680. Min Act: -0.0001
Data Index: 736893 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5193. Min Range: -6.5193
Max Act: 4.9604. Min Act: -0.0001
Data Index: 94645 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.0884. Min Act: -0.0001
Data Index: 489245 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5193. Min Range: -6.5193
Max Act: 5.4151. Min Act: -0.0001
Data Index: 1015454 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19