Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3906 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.6718. Min Act: -0.0000

Data Index: 553396 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.5359. Min Act: -0.0000

Data Index: 265251 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.4859. Min Act: -0.0000

Data Index: 369703 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.4384. Min Act: -0.0000

Data Index: 1197952 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.5538. Min Act: 0.0000

Data Index: 226879 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.5371. Min Act: -0.0000

Data Index: 1267850 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.5318. Min Act: -0.0000

Data Index: 922865 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.3750. Min Act: -0.0000

Data Index: 246430 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.1358. Min Act: -0.0000

Data Index: 251184 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.1271. Min Act: -0.0000

Data Index: 325637 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.3218. Min Act: -0.0000

Data Index: 574174 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1265918 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.2300. Min Act: 0.0000

Data Index: 402773 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.1100. Min Act: -0.0000

Data Index: 587431 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.2235. Min Act: -0.0000

Data Index: 211887 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.1014. Min Act: -0.0000

Data Index: 356855 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.2167. Min Act: -0.0000

Data Index: 94207 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.2141. Min Act: -0.0000

Data Index: 373678 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.0697. Min Act: -0.0000

Data Index: 320252 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 2.6718. Min Range: -2.6718

Max Act: 2.1998. Min Act: -0.0000

Data Index: 1139018 (C4 (Web Text))

Max Activating Token Index: 550