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

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

Neuron 71 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: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0003

Data Index: 407130 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0441. Min Act: -0.0003

Data Index: 239884 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1343516 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0420. Min Act: -0.0003

Data Index: 265969 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0400. Min Act: -0.0003

Data Index: 26174 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0397. Min Act: -0.0004

Data Index: 1175975 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0372. Min Act: -0.0003

Data Index: 49086 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0379. Min Act: -0.0003

Data Index: 784565 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0378. Min Act: -0.0003

Data Index: 8435 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0386. Min Act: -0.0004

Data Index: 760382 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1315634 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1069305 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0381. Min Act: -0.0004

Data Index: 440761 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0382. Min Act: -0.0003

Data Index: 188492 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1334166 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0381. Min Act: -0.0003

Data Index: 373328 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0365. Min Act: -0.0003

Data Index: 344276 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0358. Min Act: -0.0004

Data Index: 504412 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0367. Min Act: -0.0004

Data Index: 968617 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0365. Min Act: -0.0003

Data Index: 312452 (C4 (Web Text))

Max Activating Token Index: 191