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

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

Neuron 5051 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: 0.0312. Min Range: -0.0312

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1134388 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0310. Min Act: -0.0002

Data Index: 434833 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0275. Min Act: -0.0002

Data Index: 816056 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0274. Min Act: -0.0002

Data Index: 865386 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0271. Min Act: -0.0002

Data Index: 944341 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1109570 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0228. Min Act: -0.0002

Data Index: 550722 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0244. Min Act: -0.0002

Data Index: 652955 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0240. Min Act: -0.0002

Data Index: 120009 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1065214 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1294373 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0222. Min Act: -0.0002

Data Index: 488746 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1121208 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1301356 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0211. Min Act: -0.0002

Data Index: 296372 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0203. Min Act: -0.0002

Data Index: 883128 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0204. Min Act: -0.0002

Data Index: 286319 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1113479 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0205. Min Act: -0.0002

Data Index: 430935 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0194. Min Act: -0.0002

Data Index: 212229 (C4 (Web Text))

Max Activating Token Index: 260