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

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

Neuron 1485 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0340. Min Act: -0.0003

Data Index: 322799 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0315. Min Act: -0.0004

Data Index: 531072 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0313. Min Act: -0.0002

Data Index: 646396 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0297. Min Act: -0.0004

Data Index: 309891 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0297. Min Act: -0.0003

Data Index: 578288 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0286. Min Act: -0.0003

Data Index: 46353 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1342915 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0277. Min Act: -0.0003

Data Index: 404490 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1154381 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0269. Min Act: -0.0000

Data Index: 670766 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0270. Min Act: -0.0003

Data Index: 824751 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0263. Min Act: -0.0003

Data Index: 750053 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0265. Min Act: -0.0003

Data Index: 996366 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0263. Min Act: -0.0002

Data Index: 102453 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0266. Min Act: -0.0004

Data Index: 325108 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0257. Min Act: -0.0003

Data Index: 378191 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0255. Min Act: -0.0004

Data Index: 458724 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0261. Min Act: -0.0003

Data Index: 914596 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0260. Min Act: -0.0003

Data Index: 610966 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0261. Min Act: -0.0004

Data Index: 712089 (C4 (Web Text))

Max Activating Token Index: 277