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

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

Neuron 4551 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0003

Data Index: 7463 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1393036 (Python Code)

Max Activating Token Index: 785

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1024474 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1416066 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1434647 (Python Code)

Max Activating Token Index: 263

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1641737 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1579941 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0187. Min Act: -0.0003

Data Index: 429530 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1417363 (Python Code)

Max Activating Token Index: 67

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0202. Min Act: -0.0003

Data Index: 176876 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1384311 (Python Code)

Max Activating Token Index: 790

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0200. Min Act: -0.0003

Data Index: 542591 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1115577 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1471667 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1426471 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0212. Min Act: -0.0003

Data Index: 576001 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0187. Min Act: -0.0002

Data Index: 460352 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1407123 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0189. Min Act: -0.0003

Data Index: 176944 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0183. Min Act: -0.0003

Data Index: 519195 (C4 (Web Text))

Max Activating Token Index: 353