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

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

Neuron 2032 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: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1082488 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0564. Min Act: -0.0003

Data Index: 158455 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1058668 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1213157 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1098376 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0480. Min Act: -0.0004

Data Index: 774847 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0461. Min Act: -0.0004

Data Index: 275233 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0453. Min Act: -0.0003

Data Index: 555303 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0468. Min Act: -0.0003

Data Index: 578053 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0459. Min Act: -0.0003

Data Index: 509366 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0466. Min Act: -0.0003

Data Index: 697348 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1039823 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0454. Min Act: -0.0003

Data Index: 430147 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1275146 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0429. Min Act: -0.0004

Data Index: 1171449 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0448. Min Act: -0.0003

Data Index: 465308 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0441. Min Act: -0.0003

Data Index: 28397 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1207680 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0439. Min Act: -0.0003

Data Index: 760041 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0430. Min Act: -0.0004

Data Index: 1287264 (C4 (Web Text))

Max Activating Token Index: 353