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

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

Neuron 1422 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.4270. Min Act: -0.0000

Data Index: 550902 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.4256. Min Act: -0.0000

Data Index: 752350 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3629. Min Act: -0.0000

Data Index: 9700 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3816. Min Act: -0.0000

Data Index: 848033 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3752. Min Act: -0.0000

Data Index: 566532 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3483. Min Act: -0.0000

Data Index: 847886 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3409. Min Act: -0.0000

Data Index: 604218 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3080. Min Act: -0.0000

Data Index: 480286 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1169057 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3128. Min Act: -0.0000

Data Index: 77997 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3319. Min Act: -0.0000

Data Index: 531263 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3184. Min Act: -0.0000

Data Index: 204152 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.2986. Min Act: -0.0000

Data Index: 723335 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3340. Min Act: -0.0000

Data Index: 49589 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3065. Min Act: -0.0000

Data Index: 60779 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3047. Min Act: -0.0000

Data Index: 729164 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1227955 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.2703. Min Act: -0.0000

Data Index: 526032 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.2773. Min Act: -0.0000

Data Index: 930788 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.4270. Min Range: -0.4270

Max Act: 0.2839. Min Act: -0.0000

Data Index: 221558 (C4 (Web Text))

Max Activating Token Index: 299