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

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

Neuron 1989 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: 2.8379. Min Range: -2.8379

Max Act: 2.8379. Min Act: -0.0000

Data Index: 187746 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 2.8379. Min Range: -2.8379

Max Act: 2.5323. Min Act: -0.0000

Data Index: 326997 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 2.8379. Min Range: -2.8379

Max Act: 1.2954. Min Act: -0.0000

Data Index: 251097 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 2.8379. Min Range: -2.8379

Max Act: 1.3019. Min Act: -0.0000

Data Index: 351016 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 2.8379. Min Range: -2.8379

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1219341 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 2.8379. Min Range: -2.8379

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1028888 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 2.8379. Min Range: -2.8379

Max Act: 1.1465. Min Act: -0.0000

Data Index: 324256 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 2.8379. Min Range: -2.8379

Max Act: 1.3108. Min Act: -0.0000

Data Index: 32093 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 2.8379. Min Range: -2.8379

Max Act: 1.0725. Min Act: -0.0000

Data Index: 238306 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1234876 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.9307. Min Act: -0.0000

Data Index: 660415 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.8865. Min Act: -0.0000

Data Index: 184971 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1300477 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.9978. Min Act: -0.0000

Data Index: 627464 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1186609 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1257316 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.8700. Min Act: -0.0000

Data Index: 132028 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.8763. Min Act: -0.0000

Data Index: 973266 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1309870 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 2.8379. Min Range: -2.8379

Max Act: 0.7991. Min Act: -0.0000

Data Index: 696591 (C4 (Web Text))

Max Activating Token Index: 526