Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3620 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.1045. Min Range: -3.1045
Max Act: 3.1045. Min Act: -0.0001
Data Index: 90205 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.7501. Min Act: -0.0001
Data Index: 630594 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.5744. Min Act: -0.0001
Data Index: 266724 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.8351. Min Act: -0.0001
Data Index: 643438 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.5572. Min Act: -0.0001
Data Index: 997998 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.5773. Min Act: -0.0001
Data Index: 868494 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.3221. Min Act: -0.0001
Data Index: 1302223 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.6184. Min Act: -0.0001
Data Index: 1032772 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.3637. Min Act: -0.0001
Data Index: 720270 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.4792. Min Act: -0.0001
Data Index: 389507 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.7314. Min Act: -0.0001
Data Index: 566009 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.4763. Min Act: -0.0001
Data Index: 388195 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.2440. Min Act: -0.0001
Data Index: 1062809 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.3154. Min Act: -0.0001
Data Index: 313823 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.2918. Min Act: -0.0001
Data Index: 765796 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.5170. Min Act: -0.0001
Data Index: 711013 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.3859. Min Act: -0.0001
Data Index: 776656 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.1401. Min Act: -0.0001
Data Index: 976780 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.0974. Min Act: -0.0001
Data Index: 826297 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1045. Min Range: -3.1045
Max Act: 2.2038. Min Act: -0.0001
Data Index: 1300327 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19