Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1001 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0005

Data Index: 1629506 (Python Code)

Max Activating Token Index: 330

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1610190 (Python Code)

Max Activating Token Index: 518

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0319. Min Act: -0.0005

Data Index: 1541392 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0310. Min Act: -0.0005

Data Index: 1558853 (Python Code)

Max Activating Token Index: 840

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0299. Min Act: -0.0005

Data Index: 699403 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0285. Min Act: -0.0005

Data Index: 1590876 (Python Code)

Max Activating Token Index: 769

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0267. Min Act: -0.0005

Data Index: 1278940 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0262. Min Act: -0.0005

Data Index: 1401969 (Python Code)

Max Activating Token Index: 747

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0272. Min Act: -0.0005

Data Index: 39437 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0245. Min Act: -0.0005

Data Index: 1008051 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0266. Min Act: -0.0005

Data Index: 215332 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0250. Min Act: -0.0005

Data Index: 156005 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0252. Min Act: -0.0005

Data Index: 1579135 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1426019 (Python Code)

Max Activating Token Index: 1013

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0247. Min Act: -0.0005

Data Index: 1164865 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0256. Min Act: -0.0005

Data Index: 1149890 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0238. Min Act: -0.0005

Data Index: 233658 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0243. Min Act: -0.0005

Data Index: 1557396 (Python Code)

Max Activating Token Index: 881

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0250. Min Act: -0.0005

Data Index: 1589246 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0244. Min Act: -0.0005

Data Index: 560836 (C4 (Web Text))

Max Activating Token Index: 369