Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5294 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.8273. Min Range: -6.8273

Max Act: 6.4110. Min Act: -0.0000

Data Index: 383508 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 6.8273. Min Range: -6.8273

Max Act: 6.8273. Min Act: -0.0000

Data Index: 61824 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 6.8273. Min Range: -6.8273

Max Act: 6.3709. Min Act: -0.0000

Data Index: 898147 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.8283. Min Act: -0.0000

Data Index: 277684 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 6.8273. Min Range: -6.8273

Max Act: 6.3414. Min Act: 0.0000

Data Index: 572036 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 6.8273. Min Range: -6.8273

Max Act: 6.0228. Min Act: 0.0001

Data Index: 816240 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 6.8273. Min Range: -6.8273

Max Act: 6.1947. Min Act: -0.0000

Data Index: 420461 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 6.8273. Min Range: -6.8273

Max Act: 6.0135. Min Act: -0.0000

Data Index: 593874 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.8012. Min Act: -0.0000

Data Index: 127711 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.9905. Min Act: -0.0000

Data Index: 819017 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.9034. Min Act: 0.0001

Data Index: 349739 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.8212. Min Act: -0.0000

Data Index: 1327351 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 6.8273. Min Range: -6.8273

Max Act: 6.0414. Min Act: -0.0000

Data Index: 1114088 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.8009. Min Act: -0.0000

Data Index: 272817 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.6822. Min Act: 0.0005

Data Index: 1137661 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.2340. Min Act: -0.0000

Data Index: 598178 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.6274. Min Act: -0.0000

Data Index: 521893 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.4211. Min Act: 0.0000

Data Index: 229842 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 6.8273. Min Range: -6.8273

Max Act: 4.6916. Min Act: 0.0000

Data Index: 973862 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 6.8273. Min Range: -6.8273

Max Act: 5.6002. Min Act: -0.0000

Data Index: 1083405 (C4 (Web Text))

Max Activating Token Index: 601