Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 320 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1577. Min Act: -0.0002

Data Index: 285573 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1436. Min Act: -0.0002

Data Index: 1326250 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1350. Min Act: -0.0002

Data Index: 1104864 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1374. Min Act: -0.0002

Data Index: 1226927 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1427. Min Act: -0.0002

Data Index: 691099 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1112. Min Act: -0.0002

Data Index: 11182 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1255. Min Act: -0.0002

Data Index: 915064 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1242. Min Act: -0.0002

Data Index: 393708 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1197. Min Act: -0.0002

Data Index: 667732 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1193. Min Act: -0.0002

Data Index: 545014 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1055. Min Act: -0.0002

Data Index: 724368 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1208. Min Act: -0.0002

Data Index: 317283 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1034083 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1185. Min Act: -0.0002

Data Index: 993636 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1209. Min Act: -0.0002

Data Index: 664101 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1153. Min Act: -0.0002

Data Index: 584021 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1055. Min Act: -0.0002

Data Index: 58639 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1135. Min Act: -0.0002

Data Index: 458967 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1240. Min Act: -0.0002

Data Index: 732433 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1165. Min Act: -0.0002

Data Index: 110534 (C4 (Web Text))

Max Activating Token Index: 474