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

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

Neuron 3751 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5974. Min Act: -0.0002

Data Index: 239962 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5244. Min Act: -0.0002

Data Index: 939075 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5211. Min Act: -0.0002

Data Index: 336919 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5568. Min Act: -0.0002

Data Index: 715352 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5045. Min Act: -0.0002

Data Index: 398509 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4988. Min Act: -0.0002

Data Index: 565480 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4903. Min Act: -0.0002

Data Index: 902070 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4646. Min Act: -0.0002

Data Index: 1180967 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4440. Min Act: -0.0002

Data Index: 246141 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4900. Min Act: -0.0002

Data Index: 37393 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4274. Min Act: -0.0002

Data Index: 1035014 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5128. Min Act: -0.0002

Data Index: 558704 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4587. Min Act: -0.0002

Data Index: 1190111 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3940. Min Act: -0.0002

Data Index: 142350 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3796. Min Act: -0.0002

Data Index: 303216 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4250. Min Act: -0.0002

Data Index: 57170 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4586. Min Act: -0.0002

Data Index: 338115 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4357. Min Act: -0.0002

Data Index: 790935 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4601. Min Act: -0.0002

Data Index: 1285104 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4181. Min Act: -0.0002

Data Index: 325015 (C4 (Web Text))

Max Activating Token Index: 919