Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.4211. Min Act: -0.0000

Data Index: 435992 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.4098. Min Act: -0.0000

Data Index: 1256235 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.4232. Min Act: -0.0000

Data Index: 1243460 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.3269. Min Act: -0.0000

Data Index: 663179 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.1186. Min Act: -0.0000

Data Index: 1066012 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.3672. Min Act: -0.0000

Data Index: 1186874 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.1404. Min Act: -0.0000

Data Index: 609062 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.1349. Min Act: -0.0000

Data Index: 1344615 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.1563. Min Act: -0.0000

Data Index: 726588 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.9441. Min Act: -0.0000

Data Index: 1351395 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.0228. Min Act: -0.0000

Data Index: 450608 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.8738. Min Act: -0.0000

Data Index: 11059 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.9582. Min Act: -0.0000

Data Index: 3867 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.8187. Min Act: -0.0000

Data Index: 876922 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.9320. Min Act: -0.0000

Data Index: 1065951 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.9284. Min Act: -0.0000

Data Index: 917851 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 3.4232. Min Range: -3.4232

Max Act: 3.0725. Min Act: -0.0000

Data Index: 1060423 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.9765. Min Act: -0.0000

Data Index: 420629 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.7005. Min Act: -0.0000

Data Index: 225121 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.4232. Min Range: -3.4232

Max Act: 2.6971. Min Act: -0.0000

Data Index: 1280427 (C4 (Web Text))

Max Activating Token Index: 205