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

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

Neuron 3451 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1544404 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2406. Min Act: -0.0001

Data Index: 1648421 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2371. Min Act: 0.0001

Data Index: 1472083 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2375. Min Act: 0.0002

Data Index: 1391467 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2370. Min Act: 0.0001

Data Index: 1410298 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1307974 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1415402 (Python Code)

Max Activating Token Index: 53

Text #7

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2238. Min Act: -0.0001

Data Index: 560150 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2308. Min Act: 0.0001

Data Index: 1525925 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2221. Min Act: 0.0002

Data Index: 1426639 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2147. Min Act: 0.0002

Data Index: 1506584 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2320. Min Act: 0.0002

Data Index: 1473977 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2165. Min Act: 0.0000

Data Index: 1529338 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1590089 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2139. Min Act: 0.0001

Data Index: 1445945 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2205. Min Act: 0.0002

Data Index: 1545421 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1594684 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1441722 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1391270 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2273. Min Act: 0.0002

Data Index: 1370855 (Python Code)

Max Activating Token Index: 43