Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3172 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0000

Data Index: 617836 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0453. Min Act: -0.0000

Data Index: 355219 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0434. Min Act: -0.0000

Data Index: 138616 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0468. Min Act: -0.0000

Data Index: 639713 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0467. Min Act: -0.0000

Data Index: 226232 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1242308 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0431. Min Act: -0.0000

Data Index: 200869 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0354. Min Act: -0.0000

Data Index: 1542070 (Python Code)

Max Activating Token Index: 802

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1651888 (Python Code)

Max Activating Token Index: 926

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0365. Min Act: -0.0000

Data Index: 656132 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1403700 (Python Code)

Max Activating Token Index: 762

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0311. Min Act: -0.0000

Data Index: 802055 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0308. Min Act: -0.0000

Data Index: 434814 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1550403 (Python Code)

Max Activating Token Index: 986

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0275. Min Act: -0.0000

Data Index: 1254050 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0270. Min Act: -0.0000

Data Index: 1585603 (Python Code)

Max Activating Token Index: 774

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0263. Min Act: -0.0000

Data Index: 63822 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0292. Min Act: -0.0000

Data Index: 814409 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0271. Min Act: -0.0000

Data Index: 204760 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0269. Min Act: -0.0000

Data Index: 294154 (C4 (Web Text))

Max Activating Token Index: 518