Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 32 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0219. Min Act: -0.0001

Data Index: 202832 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1050800 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0233. Min Act: -0.0001

Data Index: 793254 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0196. Min Act: -0.0001

Data Index: 666590 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0215. Min Act: -0.0001

Data Index: 29514 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0218. Min Act: -0.0001

Data Index: 683411 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0206. Min Act: -0.0001

Data Index: 810439 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1174193 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0190. Min Act: -0.0001

Data Index: 218749 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1319678 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1387480 (Python Code)

Max Activating Token Index: 234

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1137642 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1309394 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0200. Min Act: -0.0001

Data Index: 994383 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1331641 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0184. Min Act: -0.0001

Data Index: 45000 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0182. Min Act: -0.0001

Data Index: 808490 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0187. Min Act: -0.0001

Data Index: 661777 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0183. Min Act: -0.0001

Data Index: 453369 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0001

Data Index: 420061 (C4 (Web Text))

Max Activating Token Index: 600