Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1325 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0291. Min Act: -0.0005

Data Index: 487072 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0289. Min Act: -0.0005

Data Index: 715111 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1305038 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0005

Data Index: 27720 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0284. Min Act: -0.0006

Data Index: 860574 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0296. Min Act: -0.0005

Data Index: 266363 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0258. Min Act: -0.0006

Data Index: 68469 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0278. Min Act: -0.0005

Data Index: 1217699 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0248. Min Act: -0.0006

Data Index: 382656 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0278. Min Act: -0.0006

Data Index: 905441 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0263. Min Act: -0.0005

Data Index: 1193 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0251. Min Act: -0.0006

Data Index: 263826 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0260. Min Act: -0.0006

Data Index: 565914 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0252. Min Act: -0.0006

Data Index: 149062 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1228601 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1345438 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0237. Min Act: -0.0005

Data Index: 216201 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0248. Min Act: -0.0006

Data Index: 263044 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1312550 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0255. Min Act: -0.0006

Data Index: 419827 (C4 (Web Text))

Max Activating Token Index: 892