Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 825 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0278. Min Act: -0.0006

Data Index: 853499 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0006

Data Index: 918944 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1006276 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1302833 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0248. Min Act: -0.0006

Data Index: 592581 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0254. Min Act: -0.0006

Data Index: 243027 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0252. Min Act: -0.0006

Data Index: 562748 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0256. Min Act: -0.0006

Data Index: 445739 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1369 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0242. Min Act: -0.0006

Data Index: 595814 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0252. Min Act: -0.0006

Data Index: 536101 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0240. Min Act: -0.0006

Data Index: 961486 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0240. Min Act: -0.0006

Data Index: 88480 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0250. Min Act: -0.0006

Data Index: 867296 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0249. Min Act: -0.0006

Data Index: 717698 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0249. Min Act: -0.0006

Data Index: 750170 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0243. Min Act: -0.0006

Data Index: 905110 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0247. Min Act: -0.0006

Data Index: 393249 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0237. Min Act: -0.0006

Data Index: 282678 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1202640 (C4 (Web Text))

Max Activating Token Index: 220