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

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

Neuron 488 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1319979 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0258. Min Act: -0.0006

Data Index: 93053 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0259. Min Act: -0.0006

Data Index: 488419 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0257. Min Act: -0.0006

Data Index: 251001 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1327401 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0250. Min Act: -0.0006

Data Index: 541930 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1044869 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0246. Min Act: -0.0006

Data Index: 701101 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0258. Min Act: -0.0006

Data Index: 642496 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0234. Min Act: -0.0006

Data Index: 670304 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1114894 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0006

Data Index: 928503 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0241. Min Act: -0.0006

Data Index: 965669 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1072306 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0245. Min Act: -0.0006

Data Index: 677432 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1337610 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1176789 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0249. Min Act: -0.0006

Data Index: 402544 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0249. Min Act: -0.0006

Data Index: 316008 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0242. Min Act: -0.0006

Data Index: 189362 (C4 (Web Text))

Max Activating Token Index: 44