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

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

Neuron 1776 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: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0002

Data Index: 218348 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1263309 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0333. Min Act: -0.0003

Data Index: 593781 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1096890 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1196587 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0311. Min Act: -0.0002

Data Index: 87984 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0309. Min Act: -0.0002

Data Index: 364764 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0304. Min Act: -0.0002

Data Index: 51237 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0304. Min Act: -0.0002

Data Index: 848447 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0301. Min Act: -0.0003

Data Index: 92768 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0295. Min Act: -0.0003

Data Index: 298237 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0293. Min Act: -0.0003

Data Index: 672464 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0302. Min Act: -0.0003

Data Index: 793924 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0299. Min Act: -0.0002

Data Index: 116410 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1344705 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0289. Min Act: -0.0002

Data Index: 926613 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0299. Min Act: -0.0002

Data Index: 605009 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0289. Min Act: -0.0003

Data Index: 529957 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0292. Min Act: -0.0003

Data Index: 346584 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1152787 (C4 (Web Text))

Max Activating Token Index: 526