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

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

Neuron 4430 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1630889 (Python Code)

Max Activating Token Index: 858

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0303. Min Act: -0.0003

Data Index: 202842 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1406278 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0293. Min Act: -0.0002

Data Index: 925512 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0283. Min Act: -0.0003

Data Index: 360480 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0255. Min Act: -0.0003

Data Index: 438405 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1655300 (Python Code)

Max Activating Token Index: 499

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1363124 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1435520 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0250. Min Act: -0.0003

Data Index: 470400 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0267. Min Act: -0.0003

Data Index: 514400 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0239. Min Act: -0.0003

Data Index: 892136 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0249. Min Act: -0.0003

Data Index: 809210 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1477755 (Python Code)

Max Activating Token Index: 612

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1004002 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1505748 (Python Code)

Max Activating Token Index: 804

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1537189 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1442279 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1583593 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0234. Min Act: -0.0003

Data Index: 602519 (C4 (Web Text))

Max Activating Token Index: 32