Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2605 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0332. Min Act: -0.0003

Data Index: 892969 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1346445 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1282492 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0294. Min Act: -0.0003

Data Index: 467607 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0247. Min Act: -0.0003

Data Index: 713415 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1591301 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0282. Min Act: -0.0004

Data Index: 232078 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0268. Min Act: -0.0004

Data Index: 1323425 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0268. Min Act: -0.0004

Data Index: 722890 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0258. Min Act: -0.0003

Data Index: 474757 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0265. Min Act: -0.0003

Data Index: 713664 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0260. Min Act: -0.0003

Data Index: 581400 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0265. Min Act: -0.0003

Data Index: 628680 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0242. Min Act: -0.0003

Data Index: 467821 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1123315 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1239905 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0260. Min Act: -0.0003

Data Index: 423059 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1501533 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0249. Min Act: -0.0003

Data Index: 252225 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0264. Min Act: -0.0003

Data Index: 257324 (C4 (Web Text))

Max Activating Token Index: 519