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

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

Neuron 3920 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: 3.3664. Min Range: -3.3664

Max Act: 3.3309. Min Act: -0.0000

Data Index: 1222432 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 3.3664. Min Range: -3.3664

Max Act: 3.2528. Min Act: -0.0000

Data Index: 1310313 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 3.3664. Min Range: -3.3664

Max Act: 3.3664. Min Act: -0.0001

Data Index: 1167501 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.9724. Min Act: -0.0001

Data Index: 399574 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 3.3664. Min Range: -3.3664

Max Act: 3.0740. Min Act: -0.0000

Data Index: 576493 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.9911. Min Act: -0.0000

Data Index: 1250527 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.9972. Min Act: -0.0000

Data Index: 1231106 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.7805. Min Act: -0.0000

Data Index: 750032 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 3.3664. Min Range: -3.3664

Max Act: 3.0409. Min Act: -0.0000

Data Index: 1113548 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.5370. Min Act: -0.0000

Data Index: 522657 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 3.3664. Min Range: -3.3664

Max Act: 3.2077. Min Act: -0.0000

Data Index: 1058449 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.5506. Min Act: -0.0000

Data Index: 731513 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.5279. Min Act: -0.0000

Data Index: 993312 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.4860. Min Act: -0.0000

Data Index: 588131 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.3975. Min Act: -0.0000

Data Index: 607183 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.6583. Min Act: -0.0000

Data Index: 1278130 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.6351. Min Act: -0.0000

Data Index: 1103405 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.6170. Min Act: -0.0001

Data Index: 67302 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.5550. Min Act: -0.0000

Data Index: 1077395 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 3.3664. Min Range: -3.3664

Max Act: 2.5679. Min Act: -0.0000

Data Index: 556119 (C4 (Web Text))

Max Activating Token Index: 812