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

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

Neuron 4867 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0000

Data Index: 912273 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0343. Min Act: -0.0000

Data Index: 418191 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0347. Min Act: -0.0000

Data Index: 169584 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0352. Min Act: -0.0000

Data Index: 471687 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0358. Min Act: -0.0000

Data Index: 626497 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0332. Min Act: -0.0000

Data Index: 659310 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1494463 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0366. Min Act: -0.0000

Data Index: 405877 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0312. Min Act: -0.0000

Data Index: 171218 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0325. Min Act: -0.0000

Data Index: 920757 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0319. Min Act: -0.0000

Data Index: 133198 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1274852 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0285. Min Act: -0.0000

Data Index: 1154155 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0291. Min Act: -0.0000

Data Index: 141327 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0256. Min Act: -0.0000

Data Index: 844980 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0199. Min Act: -0.0000

Data Index: 573197 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0280. Min Act: -0.0000

Data Index: 527549 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0277. Min Act: -0.0000

Data Index: 552545 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1300372 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0279. Min Act: -0.0000

Data Index: 1181477 (C4 (Web Text))

Max Activating Token Index: 84