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

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

Neuron 456 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: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0001

Data Index: 903973 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0413. Min Act: -0.0004

Data Index: 345706 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0407. Min Act: -0.0004

Data Index: 416126 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0402. Min Act: -0.0003

Data Index: 1164815 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0391. Min Act: -0.0003

Data Index: 276260 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0394. Min Act: -0.0003

Data Index: 846819 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1138141 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0372. Min Act: -0.0004

Data Index: 836399 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0357. Min Act: -0.0003

Data Index: 997145 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0357. Min Act: -0.0003

Data Index: 715036 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0353. Min Act: -0.0003

Data Index: 604880 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0360. Min Act: -0.0003

Data Index: 72045 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0345. Min Act: -0.0003

Data Index: 858174 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1162641 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0357. Min Act: -0.0003

Data Index: 515300 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0336. Min Act: -0.0003

Data Index: 840048 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0331. Min Act: -0.0003

Data Index: 230277 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0332. Min Act: -0.0003

Data Index: 961479 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0333. Min Act: -0.0002

Data Index: 491162 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0333. Min Act: -0.0003

Data Index: 972329 (C4 (Web Text))

Max Activating Token Index: 933