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

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

Neuron 4353 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1317068 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0282. Min Act: -0.0000

Data Index: 486554 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0264. Min Act: -0.0000

Data Index: 858248 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0229. Min Act: -0.0000

Data Index: 885428 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0249. Min Act: -0.0000

Data Index: 721852 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0243. Min Act: -0.0000

Data Index: 660025 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0244. Min Act: -0.0000

Data Index: 321269 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1303588 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1526086 (Python Code)

Max Activating Token Index: 671

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0248. Min Act: -0.0000

Data Index: 83451 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0238. Min Act: -0.0000

Data Index: 668921 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0231. Min Act: -0.0000

Data Index: 976232 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0289. Min Act: -0.0000

Data Index: 1277633 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0250. Min Act: -0.0000

Data Index: 702286 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1653592 (Python Code)

Max Activating Token Index: 152

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0254. Min Act: -0.0000

Data Index: 627453 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0230. Min Act: -0.0000

Data Index: 775251 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0230. Min Act: -0.0000

Data Index: 74960 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0221. Min Act: -0.0000

Data Index: 1027682 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0215. Min Act: -0.0000

Data Index: 74247 (C4 (Web Text))

Max Activating Token Index: 782