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

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

Neuron 660 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0002

Data Index: 611957 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1273999 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0296. Min Act: -0.0002

Data Index: 128206 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0298. Min Act: -0.0002

Data Index: 217543 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1276807 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0286. Min Act: -0.0002

Data Index: 357788 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0285. Min Act: -0.0002

Data Index: 534778 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1314846 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0272. Min Act: -0.0002

Data Index: 665712 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1344651 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0260. Min Act: -0.0002

Data Index: 255801 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0256. Min Act: -0.0002

Data Index: 776201 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1270545 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0249. Min Act: -0.0002

Data Index: 263551 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0248. Min Act: -0.0002

Data Index: 549428 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0243. Min Act: -0.0002

Data Index: 330722 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1168547 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1271009 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0244. Min Act: -0.0002

Data Index: 96782 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0243. Min Act: -0.0002

Data Index: 402546 (C4 (Web Text))

Max Activating Token Index: 260