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

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

Neuron 426 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: 0.0455. Min Range: -0.0455

Max Act: 0.0455. Min Act: -0.0004

Data Index: 796346 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0434. Min Act: -0.0003

Data Index: 464715 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0443. Min Act: -0.0003

Data Index: 881689 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1121055 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0410. Min Act: -0.0003

Data Index: 169102 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0391. Min Act: -0.0004

Data Index: 515394 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0390. Min Act: -0.0003

Data Index: 898603 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0395. Min Act: -0.0003

Data Index: 838335 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1123858 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1164778 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0389. Min Act: -0.0004

Data Index: 22853 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0395. Min Act: -0.0004

Data Index: 528441 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0391. Min Act: -0.0004

Data Index: 95169 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0391. Min Act: -0.0003

Data Index: 682790 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1055469 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0382. Min Act: -0.0002

Data Index: 636157 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0386. Min Act: -0.0003

Data Index: 773089 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0383. Min Act: -0.0004

Data Index: 1329191 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0384. Min Act: -0.0004

Data Index: 1347162 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1294468 (C4 (Web Text))

Max Activating Token Index: 502