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

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

Neuron 4713 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.6317. Min Act: -0.0000

Data Index: 289463 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5713. Min Act: -0.0000

Data Index: 684712 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5679. Min Act: -0.0000

Data Index: 242060 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5353. Min Act: -0.0000

Data Index: 432055 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5222. Min Act: -0.0000

Data Index: 76810 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4957. Min Act: -0.0000

Data Index: 939595 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1195402 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4635. Min Act: -0.0000

Data Index: 900957 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4785. Min Act: -0.0000

Data Index: 251236 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4602. Min Act: -0.0000

Data Index: 843128 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4706. Min Act: -0.0000

Data Index: 850412 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4407. Min Act: -0.0000

Data Index: 374043 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4240. Min Act: -0.0000

Data Index: 274497 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4351. Min Act: -0.0000

Data Index: 303441 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4517. Min Act: -0.0000

Data Index: 494250 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4335. Min Act: -0.0000

Data Index: 337247 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4314. Min Act: -0.0000

Data Index: 174699 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1149534 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4394. Min Act: -0.0000

Data Index: 418142 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4077. Min Act: -0.0000

Data Index: 533659 (C4 (Web Text))

Max Activating Token Index: 537