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

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

Neuron 1475 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: 0.0506. Min Range: -0.0506

Max Act: 0.0506. Min Act: -0.0006

Data Index: 1620448 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0298. Min Act: -0.0006

Data Index: 1642373 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0226. Min Act: -0.0006

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0267. Min Act: -0.0006

Data Index: 463047 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0277. Min Act: -0.0006

Data Index: 650453 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0277. Min Act: -0.0006

Data Index: 900079 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1248703 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1540246 (Python Code)

Max Activating Token Index: 1003

Text #8

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1415581 (Python Code)

Max Activating Token Index: 381

Text #9

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0244. Min Act: -0.0006

Data Index: 451267 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1519242 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0246. Min Act: -0.0006

Data Index: 562488 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1606435 (Python Code)

Max Activating Token Index: 796

Text #13

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0242. Min Act: -0.0005

Data Index: 1452283 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1229458 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1318584 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1410128 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0239. Min Act: -0.0006

Data Index: 51044 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0238. Min Act: -0.0006

Data Index: 516919 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1315836 (C4 (Web Text))

Max Activating Token Index: 453