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

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

Neuron 1137 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.0257. Min Act: -0.0001

Data Index: 1139538 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.2463. Min Act: -0.0000

Data Index: 542540 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.7193. Min Act: -0.0001

Data Index: 253839 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.5535. Min Act: -0.0000

Data Index: 698344 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.9771. Min Act: -0.0000

Data Index: 458792 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.7746. Min Act: -0.0001

Data Index: 603087 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.7571. Min Act: -0.0001

Data Index: 1295711 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.7162. Min Act: -0.0000

Data Index: 427875 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.6538. Min Act: -0.0001

Data Index: 757253 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.6375. Min Act: -0.0000

Data Index: 1101786 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.6322. Min Act: -0.0000

Data Index: 1253462 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.4945. Min Act: -0.0001

Data Index: 539883 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.4749. Min Act: -0.0000

Data Index: 1268835 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.4041. Min Act: -0.0000

Data Index: 1024510 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.3854. Min Act: -0.0001

Data Index: 1322857 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.3702. Min Act: -0.0001

Data Index: 212023 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.3449. Min Act: -0.0000

Data Index: 23524 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.3025. Min Act: -0.0001

Data Index: 65019 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.3753. Min Act: -0.0001

Data Index: 795294 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 3.2463. Min Range: -3.2463

Max Act: 2.0420. Min Act: -0.0001

Data Index: 564433 (C4 (Web Text))

Max Activating Token Index: 259