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

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

Neuron 1452 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0390. Min Act: -0.0002

Data Index: 519816 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0401. Min Act: -0.0002

Data Index: 387329 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0417. Min Act: -0.0002

Data Index: 735982 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0323. Min Act: -0.0002

Data Index: 941578 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0327. Min Act: -0.0002

Data Index: 100566 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0358. Min Act: -0.0002

Data Index: 90367 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1121372 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0385. Min Act: -0.0002

Data Index: 931086 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1038778 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1354857 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0263. Min Act: -0.0002

Data Index: 108436 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1102061 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0308. Min Act: -0.0002

Data Index: 692134 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0321. Min Act: -0.0002

Data Index: 226647 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0409. Min Act: -0.0002

Data Index: 234991 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0238. Min Act: -0.0002

Data Index: 519384 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0211. Min Act: -0.0002

Data Index: 839812 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0238. Min Act: -0.0002

Data Index: 295213 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0187. Min Act: -0.0002

Data Index: 841224 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1020660 (C4 (Web Text))

Max Activating Token Index: 311