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

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

Neuron 4250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.6573. Min Act: -0.0000

Data Index: 440860 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5240. Min Act: -0.0000

Data Index: 880107 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5696. Min Act: -0.0000

Data Index: 170903 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1283265 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1358438 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4728. Min Act: -0.0000

Data Index: 583256 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4974. Min Act: -0.0000

Data Index: 636467 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4899. Min Act: -0.0000

Data Index: 469406 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4564. Min Act: -0.0000

Data Index: 137173 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4307. Min Act: -0.0000

Data Index: 18292 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4548. Min Act: -0.0001

Data Index: 1120099 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4803. Min Act: -0.0000

Data Index: 392503 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1122440 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1171201 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1043241 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4372. Min Act: -0.0000

Data Index: 520223 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1094700 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4401. Min Act: -0.0000

Data Index: 829371 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4321. Min Act: -0.0000

Data Index: 46844 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4326. Min Act: -0.0000

Data Index: 631462 (C4 (Web Text))

Max Activating Token Index: 202