Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 406 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.3485. Min Act: -0.0001

Data Index: 1240239 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.2097. Min Act: -0.0001

Data Index: 1168997 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1352362 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.1813. Min Act: -0.0000

Data Index: 338546 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.1394. Min Act: -0.0000

Data Index: 645584 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.1425. Min Act: -0.0000

Data Index: 932485 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.0428. Min Act: -0.0000

Data Index: 624494 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.0860. Min Act: -0.0000

Data Index: 926736 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.0255. Min Act: -0.0001

Data Index: 525454 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.0834. Min Act: -0.0001

Data Index: 1507621 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9785. Min Act: -0.0001

Data Index: 91702 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9704. Min Act: -0.0001

Data Index: 971377 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9563. Min Act: -0.0000

Data Index: 255180 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9785. Min Act: -0.0001

Data Index: 336607 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.0005. Min Act: -0.0001

Data Index: 1193322 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9161. Min Act: -0.0000

Data Index: 396214 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9718. Min Act: -0.0000

Data Index: 293066 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9813. Min Act: -0.0000

Data Index: 261998 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8680. Min Act: -0.0001

Data Index: 1157411 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9612. Min Act: -0.0001

Data Index: 1513066 (Python Code)

Max Activating Token Index: 301