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

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

Neuron 5103 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1158207 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0000

Data Index: 933450 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0287. Min Act: -0.0000

Data Index: 909820 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0292. Min Act: -0.0000

Data Index: 1548839 (Python Code)

Max Activating Token Index: 930

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0265. Min Act: -0.0000

Data Index: 1257730 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0258. Min Act: -0.0000

Data Index: 1603343 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0264. Min Act: -0.0000

Data Index: 1384536 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0255. Min Act: -0.0000

Data Index: 729925 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0255. Min Act: -0.0000

Data Index: 720430 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0252. Min Act: -0.0000

Data Index: 1349730 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0249. Min Act: -0.0000

Data Index: 822045 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0242. Min Act: -0.0000

Data Index: 1339916 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0247. Min Act: -0.0000

Data Index: 733654 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0262. Min Act: -0.0000

Data Index: 132025 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0245. Min Act: -0.0000

Data Index: 676906 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0221. Min Act: -0.0000

Data Index: 941733 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1095413 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0236. Min Act: -0.0000

Data Index: 1125266 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0249. Min Act: -0.0000

Data Index: 1577799 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1642581 (Python Code)

Max Activating Token Index: 943