Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1840 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0002

Data Index: 196729 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0372. Min Act: -0.0002

Data Index: 694772 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0320. Min Act: -0.0002

Data Index: 191451 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0262. Min Act: -0.0002

Data Index: 622670 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0287. Min Act: -0.0002

Data Index: 273004 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1355918 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0287. Min Act: -0.0002

Data Index: 583906 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0257. Min Act: -0.0002

Data Index: 392497 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1199156 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0255. Min Act: -0.0002

Data Index: 336217 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1239747 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0244. Min Act: -0.0002

Data Index: 147313 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1056614 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0243. Min Act: -0.0002

Data Index: 432983 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0232. Min Act: -0.0002

Data Index: 982640 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0247. Min Act: -0.0002

Data Index: 974087 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0243. Min Act: -0.0002

Data Index: 81491 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0209. Min Act: -0.0002

Data Index: 383821 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0252. Min Act: -0.0002

Data Index: 791655 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0242. Min Act: -0.0002

Data Index: 362016 (C4 (Web Text))

Max Activating Token Index: 449