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

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

Neuron 3975 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.4027. Min Act: -0.0000

Data Index: 741391 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.3765. Min Act: -0.0000

Data Index: 211183 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.4908. Min Act: -0.0000

Data Index: 1034994 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.4428. Min Act: -0.0000

Data Index: 696405 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.3636. Min Act: -0.0000

Data Index: 824574 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.4139. Min Act: -0.0000

Data Index: 898778 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.3940. Min Act: -0.0000

Data Index: 400477 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.4144. Min Act: -0.0000

Data Index: 411269 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.3277. Min Act: -0.0000

Data Index: 939281 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.3651. Min Act: -0.0000

Data Index: 296419 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.3551. Min Act: -0.0000

Data Index: 525242 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.3921. Min Act: -0.0000

Data Index: 49185 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.2807. Min Act: -0.0000

Data Index: 1237687 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.3237. Min Act: -0.0000

Data Index: 790236 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1132988 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.1861. Min Act: -0.0000

Data Index: 1110816 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1116692 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.1857. Min Act: -0.0000

Data Index: 968731 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.1771. Min Act: -0.0000

Data Index: 490517 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 1.4908. Min Range: -1.4908

Max Act: 1.2349. Min Act: -0.0000

Data Index: 385613 (C4 (Web Text))

Max Activating Token Index: 813