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

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

Neuron 428 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2813. Min Act: -0.0001

Data Index: 1164251 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2587. Min Act: -0.0001

Data Index: 389842 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2562. Min Act: -0.0001

Data Index: 924244 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2516. Min Act: -0.0001

Data Index: 345258 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2565. Min Act: -0.0001

Data Index: 138544 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2385. Min Act: -0.0001

Data Index: 748373 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2440. Min Act: -0.0001

Data Index: 839191 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2517. Min Act: -0.0001

Data Index: 964458 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2426. Min Act: -0.0001

Data Index: 111032 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2354. Min Act: -0.0001

Data Index: 1163238 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1154394 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2340. Min Act: -0.0001

Data Index: 677401 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2405. Min Act: -0.0001

Data Index: 967192 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2408. Min Act: -0.0001

Data Index: 646573 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2314. Min Act: -0.0001

Data Index: 1302110 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2299. Min Act: -0.0001

Data Index: 703764 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2209. Min Act: -0.0001

Data Index: 1349884 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2282. Min Act: -0.0001

Data Index: 680163 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1275280 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2365. Min Act: -0.0001

Data Index: 400177 (C4 (Web Text))

Max Activating Token Index: 979