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

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

Neuron 4787 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1303028 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0521. Min Act: -0.0002

Data Index: 620143 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0368. Min Act: -0.0002

Data Index: 465530 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0333. Min Act: -0.0002

Data Index: 364532 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0293. Min Act: -0.0002

Data Index: 287554 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0270. Min Act: -0.0002

Data Index: 608376 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0262. Min Act: -0.0002

Data Index: 329230 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1110663 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0251. Min Act: -0.0002

Data Index: 693193 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0247. Min Act: -0.0002

Data Index: 40853 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0247. Min Act: -0.0002

Data Index: 411816 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0247. Min Act: -0.0001

Data Index: 660925 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0240. Min Act: -0.0001

Data Index: 601536 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0239. Min Act: -0.0002

Data Index: 848985 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0244. Min Act: -0.0002

Data Index: 441431 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0237. Min Act: -0.0002

Data Index: 212488 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0239. Min Act: -0.0002

Data Index: 676996 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0233. Min Act: -0.0002

Data Index: 43519 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1270296 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1213168 (C4 (Web Text))

Max Activating Token Index: 762