Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3693 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0001

Data Index: 206901 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0380. Min Act: -0.0001

Data Index: 539204 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0356. Min Act: -0.0002

Data Index: 355380 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0320. Min Act: -0.0001

Data Index: 476503 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1196374 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0316. Min Act: -0.0001

Data Index: 825599 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0322. Min Act: -0.0001

Data Index: 33525 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1499628 (Python Code)

Max Activating Token Index: 720

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0277. Min Act: -0.0002

Data Index: 461063 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1623448 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1599979 (Python Code)

Max Activating Token Index: 990

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0290. Min Act: -0.0001

Data Index: 918975 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0250. Min Act: -0.0001

Data Index: 34631 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0279. Min Act: -0.0001

Data Index: 968180 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0243. Min Act: -0.0002

Data Index: 635280 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0239. Min Act: -0.0001

Data Index: 432395 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1572470 (Python Code)

Max Activating Token Index: 616

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0235. Min Act: -0.0001

Data Index: 132250 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1095419 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1653519 (Python Code)

Max Activating Token Index: 1015