Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 450 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1164902 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0232. Min Act: -0.0006

Data Index: 312988 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0225. Min Act: -0.0006

Data Index: 754748 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0225. Min Act: -0.0006

Data Index: 655222 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0222. Min Act: -0.0005

Data Index: 1556926 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0220. Min Act: -0.0006

Data Index: 595746 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0225. Min Act: -0.0006

Data Index: 426802 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0214. Min Act: -0.0006

Data Index: 296054 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0218. Min Act: -0.0006

Data Index: 763104 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0207. Min Act: -0.0006

Data Index: 954431 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0201. Min Act: -0.0006

Data Index: 680990 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0215. Min Act: -0.0006

Data Index: 132582 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0218. Min Act: -0.0006

Data Index: 106932 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0217. Min Act: -0.0006

Data Index: 149446 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1353425 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0207. Min Act: -0.0006

Data Index: 88758 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0210. Min Act: -0.0006

Data Index: 164780 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1190423 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0201. Min Act: -0.0006

Data Index: 395854 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0210. Min Act: -0.0006

Data Index: 758189 (C4 (Web Text))

Max Activating Token Index: 971