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

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

Neuron 1723 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: 0.6834. Min Range: -0.6834

Max Act: 0.6834. Min Act: -0.0002

Data Index: 1388406 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4345. Min Act: -0.0002

Data Index: 627654 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.3456. Min Act: -0.0002

Data Index: 914857 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.3255. Min Act: -0.0002

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.3220. Min Act: -0.0002

Data Index: 912217 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2770. Min Act: -0.0002

Data Index: 277658 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2890. Min Act: -0.0002

Data Index: 748807 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.3016. Min Act: -0.0002

Data Index: 289450 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2664. Min Act: -0.0002

Data Index: 1482606 (Python Code)

Max Activating Token Index: 448

Text #9

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2599. Min Act: -0.0002

Data Index: 650064 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2507. Min Act: -0.0002

Data Index: 1344090 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2409. Min Act: -0.0002

Data Index: 1387063 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2578. Min Act: -0.0002

Data Index: 1480782 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2540. Min Act: -0.0002

Data Index: 1640440 (Python Code)

Max Activating Token Index: 513

Text #14

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2358. Min Act: -0.0002

Data Index: 268833 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2509. Min Act: -0.0002

Data Index: 1628462 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2586. Min Act: -0.0002

Data Index: 897226 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2351. Min Act: -0.0002

Data Index: 1393365 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2351. Min Act: -0.0002

Data Index: 971910 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.2338. Min Act: -0.0002

Data Index: 726953 (C4 (Web Text))

Max Activating Token Index: 759