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

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

Neuron 4520 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1357796 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.4068. Min Act: -0.0000

Data Index: 667165 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3324. Min Act: -0.0000

Data Index: 612063 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1220493 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1163278 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2987. Min Act: -0.0000

Data Index: 877036 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2243. Min Act: -0.0000

Data Index: 896632 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2463. Min Act: -0.0000

Data Index: 372019 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1162506 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1307972 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2178. Min Act: -0.0000

Data Index: 751892 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1251636 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1108246 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2225. Min Act: -0.0000

Data Index: 471027 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2163. Min Act: -0.0000

Data Index: 207747 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1125454 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2123. Min Act: -0.0000

Data Index: 18384 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.2283. Min Act: -0.0000

Data Index: 933795 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1228619 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.4068. Min Range: -0.4068

Max Act: 0.1881. Min Act: -0.0000

Data Index: 253637 (C4 (Web Text))

Max Activating Token Index: 250