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

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

Neuron 1690 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.8479. Min Act: -0.0000

Data Index: 610912 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.1859. Min Act: -0.0000

Data Index: 369621 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.1362. Min Act: -0.0000

Data Index: 1350172 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.2271. Min Act: -0.0000

Data Index: 293647 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.1205. Min Act: -0.0000

Data Index: 173723 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.1056. Min Act: -0.0000

Data Index: 1169307 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.0659. Min Act: -0.0000

Data Index: 181919 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.0229. Min Act: -0.0000

Data Index: 1298877 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.9369. Min Act: -0.0000

Data Index: 904602 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.0219. Min Act: -0.0000

Data Index: 1318445 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.7848. Min Act: -0.0000

Data Index: 987669 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.7631. Min Act: -0.0000

Data Index: 892002 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.7388. Min Act: -0.0000

Data Index: 1314376 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.8382. Min Act: -0.0000

Data Index: 1219744 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.8216. Min Act: -0.0000

Data Index: 816262 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.8310. Min Act: -0.0000

Data Index: 747018 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.8220. Min Act: -0.0000

Data Index: 539065 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.8163. Min Act: -0.0000

Data Index: 643576 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.8113. Min Act: -0.0000

Data Index: 1077253 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 2.8479. Min Range: -2.8479

Max Act: 1.8944. Min Act: -0.0000

Data Index: 480977 (C4 (Web Text))

Max Activating Token Index: 585