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

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

Neuron 1322 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: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0005

Data Index: 1363266 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0314. Min Act: -0.0006

Data Index: 1061621 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0296. Min Act: -0.0006

Data Index: 363923 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1496724 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0254. Min Act: -0.0006

Data Index: 674469 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1469213 (Python Code)

Max Activating Token Index: 401

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0278. Min Act: -0.0006

Data Index: 905493 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1566511 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0239. Min Act: -0.0006

Data Index: 827852 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1636882 (Python Code)

Max Activating Token Index: 932

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1546727 (Python Code)

Max Activating Token Index: 1020

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0253. Min Act: -0.0006

Data Index: 325656 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1427937 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0235. Min Act: -0.0006

Data Index: 967445 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1095680 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1118926 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1652012 (Python Code)

Max Activating Token Index: 440

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1149534 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0241. Min Act: -0.0006

Data Index: 942990 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1268837 (C4 (Web Text))

Max Activating Token Index: 128