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

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

Neuron 4530 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1203487 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.3150. Min Act: -0.0000

Data Index: 171311 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1150237 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2821. Min Act: -0.0000

Data Index: 419684 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1070255 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2870. Min Act: -0.0000

Data Index: 149696 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2878. Min Act: -0.0000

Data Index: 237825 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1280529 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1180206 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2845. Min Act: -0.0000

Data Index: 145702 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2815. Min Act: -0.0000

Data Index: 529752 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2590. Min Act: -0.0000

Data Index: 280946 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2693. Min Act: -0.0000

Data Index: 188350 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2469. Min Act: -0.0000

Data Index: 613655 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2352. Min Act: -0.0000

Data Index: 248850 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2316. Min Act: -0.0000

Data Index: 596864 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1287308 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2229. Min Act: -0.0000

Data Index: 421872 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2356. Min Act: -0.0000

Data Index: 523212 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.3377. Min Range: -0.3377

Max Act: 0.2269. Min Act: -0.0000

Data Index: 484325 (C4 (Web Text))

Max Activating Token Index: 234