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

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

Neuron 88 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: 0.8299. Min Range: -0.8299

Max Act: 0.8299. Min Act: -0.0002

Data Index: 868070 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.7919. Min Act: -0.0002

Data Index: 775518 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.6940. Min Act: -0.0002

Data Index: 448298 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.5948. Min Act: -0.0002

Data Index: 553617 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.5381. Min Act: -0.0002

Data Index: 334518 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.5034. Min Act: -0.0002

Data Index: 1312724 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.6804. Min Act: -0.0002

Data Index: 399635 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.6155. Min Act: -0.0002

Data Index: 275816 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.6076. Min Act: -0.0002

Data Index: 775406 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.6296. Min Act: -0.0002

Data Index: 846578 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.5178. Min Act: -0.0002

Data Index: 963267 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.4990. Min Act: -0.0002

Data Index: 1324343 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.5206. Min Act: -0.0002

Data Index: 1114752 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.4257. Min Act: -0.0002

Data Index: 899518 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.4996. Min Act: -0.0002

Data Index: 945058 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.5236. Min Act: -0.0002

Data Index: 1317018 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.5072. Min Act: -0.0002

Data Index: 1191482 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.5282. Min Act: -0.0002

Data Index: 1058050 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.4917. Min Act: -0.0002

Data Index: 1305949 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.8299. Min Range: -0.8299

Max Act: 0.5261. Min Act: -0.0002

Data Index: 130032 (C4 (Web Text))

Max Activating Token Index: 928