Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 178 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0321. Min Act: -0.0003

Data Index: 751598 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0312. Min Act: -0.0004

Data Index: 503571 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0298. Min Act: -0.0002

Data Index: 124442 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0297. Min Act: -0.0003

Data Index: 384952 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0296. Min Act: -0.0002

Data Index: 782460 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0297. Min Act: -0.0003

Data Index: 599091 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0293. Min Act: -0.0003

Data Index: 952895 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1083445 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0290. Min Act: -0.0002

Data Index: 415011 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0302. Min Act: -0.0003

Data Index: 736767 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0286. Min Act: -0.0002

Data Index: 298005 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0289. Min Act: -0.0003

Data Index: 378224 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0283. Min Act: -0.0002

Data Index: 610600 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1267385 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0285. Min Act: -0.0004

Data Index: 871252 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0287. Min Act: -0.0002

Data Index: 361397 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1343404 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0275. Min Act: -0.0002

Data Index: 108353 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0277. Min Act: -0.0002

Data Index: 74157 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0283. Min Act: -0.0003

Data Index: 801700 (C4 (Web Text))

Max Activating Token Index: 554