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

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

Neuron 2358 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0001

Data Index: 925884 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0295. Min Act: -0.0000

Data Index: 264542 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0290. Min Act: -0.0000

Data Index: 914451 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0276. Min Act: -0.0000

Data Index: 396760 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0269. Min Act: -0.0000

Data Index: 704872 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0287. Min Act: -0.0000

Data Index: 225248 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1423768 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0256. Min Act: -0.0000

Data Index: 287965 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0243. Min Act: -0.0000

Data Index: 162611 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1103658 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0238. Min Act: -0.0000

Data Index: 1483219 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0247. Min Act: -0.0000

Data Index: 1212998 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1490983 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0299. Min Act: -0.0001

Data Index: 972940 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0237. Min Act: -0.0000

Data Index: 777078 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0260. Min Act: -0.0000

Data Index: 166303 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0232. Min Act: -0.0000

Data Index: 1057963 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0247. Min Act: -0.0001

Data Index: 516729 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1388958 (Python Code)

Max Activating Token Index: 815

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0237. Min Act: -0.0000

Data Index: 1652556 (Python Code)

Max Activating Token Index: 674