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

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

Neuron 745 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 737355 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0230. Min Act: -0.0003

Data Index: 150096 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1014275 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0215. Min Act: -0.0003

Data Index: 109805 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0205. Min Act: -0.0002

Data Index: 884638 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0202. Min Act: -0.0003

Data Index: 21686 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0197. Min Act: -0.0003

Data Index: 980658 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1320187 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0201. Min Act: -0.0002

Data Index: 839936 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0198. Min Act: -0.0003

Data Index: 939496 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0203. Min Act: -0.0003

Data Index: 218122 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0205. Min Act: -0.0002

Data Index: 666790 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0198. Min Act: -0.0003

Data Index: 675689 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1121820 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0201. Min Act: -0.0002

Data Index: 265827 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0200. Min Act: -0.0003

Data Index: 186021 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0193. Min Act: -0.0003

Data Index: 636053 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0195. Min Act: -0.0003

Data Index: 896852 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0192. Min Act: -0.0002

Data Index: 965292 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0200. Min Act: -0.0002

Data Index: 687119 (C4 (Web Text))

Max Activating Token Index: 633