Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4850 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0904. Min Range: -1.0904

Max Act: 1.0904. Min Act: -0.0000

Data Index: 179627 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9813. Min Act: -0.0000

Data Index: 950713 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 1.0904. Min Range: -1.0904

Max Act: 1.0152. Min Act: -0.0000

Data Index: 751341 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9713. Min Act: -0.0000

Data Index: 342768 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9278. Min Act: -0.0000

Data Index: 443044 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9522. Min Act: -0.0000

Data Index: 204796 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1204975 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8841. Min Act: -0.0000

Data Index: 429425 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8814. Min Act: -0.0000

Data Index: 308414 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1234613 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8525. Min Act: -0.0000

Data Index: 174885 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1284149 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7539. Min Act: -0.0000

Data Index: 535158 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8086. Min Act: -0.0000

Data Index: 827504 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7734. Min Act: -0.0000

Data Index: 411882 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7374. Min Act: -0.0000

Data Index: 589171 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8084. Min Act: -0.0000

Data Index: 767963 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8061. Min Act: -0.0000

Data Index: 806839 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7812. Min Act: -0.0000

Data Index: 105339 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7639. Min Act: -0.0000

Data Index: 341455 (C4 (Web Text))

Max Activating Token Index: 518