Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4192 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0001

Data Index: 108590 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0471. Min Act: -0.0001

Data Index: 312469 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0460. Min Act: -0.0001

Data Index: 976721 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0394. Min Act: -0.0001

Data Index: 698267 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1405959 (Python Code)

Max Activating Token Index: 493

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0333. Min Act: -0.0001

Data Index: 397354 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0351. Min Act: -0.0001

Data Index: 682676 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1364383 (Python Code)

Max Activating Token Index: 894

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1543658 (Python Code)

Max Activating Token Index: 633

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0321. Min Act: -0.0001

Data Index: 120368 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1388988 (Python Code)

Max Activating Token Index: 352

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0310. Min Act: -0.0001

Data Index: 28535 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1364761 (Python Code)

Max Activating Token Index: 848

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0265. Min Act: -0.0001

Data Index: 203804 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1447766 (Python Code)

Max Activating Token Index: 442

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1420996 (Python Code)

Max Activating Token Index: 253

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1449897 (Python Code)

Max Activating Token Index: 573

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1485867 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0274. Min Act: -0.0001

Data Index: 962697 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1461614 (Python Code)

Max Activating Token Index: 687