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

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

Neuron 668 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: 0.0428. Min Range: -0.0428

Max Act: 0.0427. Min Act: -0.0002

Data Index: 867999 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1315291 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0002

Data Index: 725849 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1304818 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0389. Min Act: -0.0002

Data Index: 82302 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1448985 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0332. Min Act: -0.0002

Data Index: 7037 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0332. Min Act: -0.0002

Data Index: 77381 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0332. Min Act: -0.0002

Data Index: 58391 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0334. Min Act: -0.0002

Data Index: 474460 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0308. Min Act: -0.0002

Data Index: 446607 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0325. Min Act: -0.0002

Data Index: 949705 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0292. Min Act: -0.0002

Data Index: 863808 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0270. Min Act: -0.0002

Data Index: 562334 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0329. Min Act: -0.0002

Data Index: 204963 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0280. Min Act: -0.0002

Data Index: 775222 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1124573 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0304. Min Act: -0.0002

Data Index: 992896 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0323. Min Act: -0.0002

Data Index: 489858 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0344. Min Act: -0.0002

Data Index: 151061 (C4 (Web Text))

Max Activating Token Index: 541