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

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

Neuron 68 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: 0.0292. Min Range: -0.0292

Max Act: 0.0292. Min Act: -0.0006

Data Index: 358778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0277. Min Act: -0.0006

Data Index: 85034 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0267. Min Act: -0.0006

Data Index: 152304 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0254. Min Act: -0.0006

Data Index: 72594 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0260. Min Act: -0.0006

Data Index: 184051 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0247. Min Act: -0.0006

Data Index: 398304 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1446870 (Python Code)

Max Activating Token Index: 478

Text #7

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0234. Min Act: -0.0006

Data Index: 71579 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0229. Min Act: -0.0006

Data Index: 463381 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0230. Min Act: -0.0006

Data Index: 777239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0224. Min Act: -0.0006

Data Index: 901730 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0229. Min Act: -0.0006

Data Index: 149877 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1132377 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0231. Min Act: -0.0006

Data Index: 385864 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0225. Min Act: -0.0006

Data Index: 438598 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1032679 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0229. Min Act: -0.0005

Data Index: 1275499 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0216. Min Act: -0.0006

Data Index: 720109 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0214. Min Act: -0.0006

Data Index: 35032 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1024627 (C4 (Web Text))

Max Activating Token Index: 85