Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4488 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2741. Min Act: -0.0001
Data Index: 350093 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2585. Min Act: -0.0001
Data Index: 1256628 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2585. Min Act: -0.0000
Data Index: 1062297 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2229. Min Act: -0.0001
Data Index: 887614 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2327. Min Act: -0.0001
Data Index: 1556595 (Python Code)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2472. Min Act: -0.0000
Data Index: 574524 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2414. Min Act: -0.0000
Data Index: 452614 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2350. Min Act: -0.0001
Data Index: 1147238 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2400. Min Act: -0.0001
Data Index: 884418 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2412. Min Act: -0.0001
Data Index: 1143412 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2247. Min Act: -0.0001
Data Index: 41469 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2074. Min Act: -0.0001
Data Index: 992621 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2400. Min Act: -0.0000
Data Index: 1176893 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2243. Min Act: -0.0001
Data Index: 311119 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2330. Min Act: -0.0001
Data Index: 304011 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.1916. Min Act: -0.0001
Data Index: 614711 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2347. Min Act: -0.0001
Data Index: 1211301 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2125. Min Act: -0.0001
Data Index: 1108568 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.1935. Min Act: -0.0001
Data Index: 757995 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2741. Min Range: -0.2741
Max Act: 0.2082. Min Act: -0.0001
Data Index: 1350032 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19