Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2772 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7880. Min Range: -2.7880
Max Act: 2.7880. Min Act: -0.0001
Data Index: 391597 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.4365. Min Act: -0.0001
Data Index: 17016 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.3940. Min Act: -0.0001
Data Index: 571793 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.3133. Min Act: -0.0001
Data Index: 463022 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.3707. Min Act: -0.0001
Data Index: 232025 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.1048. Min Act: -0.0001
Data Index: 15694 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.2938. Min Act: -0.0001
Data Index: 1320572 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.2323. Min Act: -0.0001
Data Index: 26339 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.0877. Min Act: -0.0001
Data Index: 564879 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.1582. Min Act: -0.0001
Data Index: 465096 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.0447. Min Act: -0.0001
Data Index: 1059806 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.1358. Min Act: -0.0001
Data Index: 544962 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.1756. Min Act: -0.0001
Data Index: 222369 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.1947. Min Act: -0.0001
Data Index: 226298 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.1948. Min Act: -0.0001
Data Index: 626527 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.1602. Min Act: -0.0001
Data Index: 453891 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.0913. Min Act: -0.0001
Data Index: 889901 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.0788. Min Act: -0.0001
Data Index: 329512 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.1509. Min Act: -0.0001
Data Index: 304727 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7880. Min Range: -2.7880
Max Act: 1.2429. Min Act: -0.0001
Data Index: 1342824 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19