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

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

Neuron 4997 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0000

Data Index: 898077 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0242. Min Act: -0.0001

Data Index: 136913 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0234. Min Act: -0.0001

Data Index: 245071 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0240. Min Act: -0.0000

Data Index: 432459 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0226. Min Act: -0.0001

Data Index: 460068 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1041557 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0223. Min Act: -0.0000

Data Index: 470231 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0206. Min Act: -0.0001

Data Index: 830841 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0219. Min Act: -0.0001

Data Index: 801914 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0223. Min Act: -0.0000

Data Index: 116580 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0184. Min Act: -0.0001

Data Index: 388060 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0191. Min Act: -0.0000

Data Index: 1201029 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0209. Min Act: -0.0001

Data Index: 586967 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0210. Min Act: -0.0000

Data Index: 1225298 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0205. Min Act: -0.0001

Data Index: 640720 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0207. Min Act: -0.0001

Data Index: 493616 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0185. Min Act: -0.0000

Data Index: 183161 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0211. Min Act: -0.0001

Data Index: 1637487 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0206. Min Act: -0.0001

Data Index: 187660 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1259831 (C4 (Web Text))

Max Activating Token Index: 753