Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 840 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1116731 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0563. Min Act: -0.0003

Data Index: 875120 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0509. Min Act: -0.0003

Data Index: 641734 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0503. Min Act: -0.0003

Data Index: 622858 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1011851 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0538. Min Act: -0.0004

Data Index: 1017048 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0485. Min Act: -0.0003

Data Index: 124263 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0483. Min Act: -0.0003

Data Index: 712204 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1238690 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0470. Min Act: -0.0003

Data Index: 303643 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1263420 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0478. Min Act: -0.0003

Data Index: 348282 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0467. Min Act: -0.0003

Data Index: 886706 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0484. Min Act: -0.0003

Data Index: 669497 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0457. Min Act: -0.0003

Data Index: 304989 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1132233 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0453. Min Act: -0.0003

Data Index: 252353 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0458. Min Act: -0.0003

Data Index: 143671 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0435. Min Act: -0.0003

Data Index: 265100 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0460. Min Act: -0.0003

Data Index: 952418 (C4 (Web Text))

Max Activating Token Index: 611