Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2384 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0004

Data Index: 453243 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0271. Min Act: -0.0004

Data Index: 61744 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0270. Min Act: -0.0004

Data Index: 648625 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0274. Min Act: -0.0004

Data Index: 923207 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0235. Min Act: -0.0004

Data Index: 276621 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0252. Min Act: -0.0004

Data Index: 399468 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0268. Min Act: -0.0004

Data Index: 483127 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0232. Min Act: -0.0004

Data Index: 646611 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0237. Min Act: -0.0004

Data Index: 301320 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0245. Min Act: -0.0004

Data Index: 129633 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1144094 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0176. Min Act: -0.0004

Data Index: 684532 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0233. Min Act: -0.0004

Data Index: 202818 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0268. Min Act: -0.0004

Data Index: 522231 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0254. Min Act: -0.0004

Data Index: 830405 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0242. Min Act: -0.0004

Data Index: 911949 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0214. Min Act: -0.0004

Data Index: 251967 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0273. Min Act: -0.0004

Data Index: 305097 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0250. Min Act: -0.0004

Data Index: 1017811 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0186. Min Act: -0.0004

Data Index: 368789 (C4 (Web Text))

Max Activating Token Index: 791