Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3290 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.4493. Min Act: -0.0000
Data Index: 1003285 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2211. Min Act: -0.0000
Data Index: 593036 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.1087. Min Act: -0.0001
Data Index: 399447 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.8037. Min Act: -0.0001
Data Index: 73691 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.7068. Min Act: -0.0001
Data Index: 306343 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.8228. Min Act: -0.0000
Data Index: 76027 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.7534. Min Act: -0.0001
Data Index: 399526 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.7412. Min Act: -0.0001
Data Index: 1250388 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.6528. Min Act: -0.0001
Data Index: 661021 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.7180. Min Act: -0.0001
Data Index: 710893 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.6012. Min Act: -0.0000
Data Index: 643278 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.5026. Min Act: -0.0001
Data Index: 223028 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.4512. Min Act: -0.0001
Data Index: 604085 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.5833. Min Act: -0.0001
Data Index: 898402 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.5852. Min Act: -0.0001
Data Index: 1330901 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.5405. Min Act: -0.0000
Data Index: 236633 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.5807. Min Act: -0.0001
Data Index: 1293118 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.4471. Min Act: -0.0001
Data Index: 309991 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.5139. Min Act: -0.0001
Data Index: 887764 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4493. Min Range: -2.4493
Max Act: 1.4295. Min Act: -0.0001
Data Index: 245901 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19