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

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

Neuron 300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0236. Min Act: -0.0003

Data Index: 669088 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0211. Min Act: -0.0003

Data Index: 210021 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0227. Min Act: -0.0002

Data Index: 276642 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0220. Min Act: -0.0003

Data Index: 599901 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0218. Min Act: -0.0003

Data Index: 330611 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1001859 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0211. Min Act: -0.0003

Data Index: 238795 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0199. Min Act: -0.0003

Data Index: 46198 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0205. Min Act: -0.0003

Data Index: 245227 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0218. Min Act: -0.0003

Data Index: 242640 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0200. Min Act: -0.0003

Data Index: 319577 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0204. Min Act: -0.0002

Data Index: 11266 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0208. Min Act: -0.0003

Data Index: 96118 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0200. Min Act: -0.0002

Data Index: 740011 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1023067 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0205. Min Act: -0.0002

Data Index: 33679 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0195. Min Act: -0.0002

Data Index: 763035 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1337157 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0197. Min Act: -0.0003

Data Index: 350384 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0204. Min Act: -0.0003

Data Index: 650005 (C4 (Web Text))

Max Activating Token Index: 359