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

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

Neuron 1524 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: 0.7827. Min Range: -0.7827

Max Act: 0.7827. Min Act: -0.0000

Data Index: 69433 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7314. Min Act: -0.0000

Data Index: 918624 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7065. Min Act: -0.0000

Data Index: 917777 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6474. Min Act: -0.0000

Data Index: 503592 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6631. Min Act: -0.0000

Data Index: 230939 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5949. Min Act: -0.0000

Data Index: 960278 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5314. Min Act: -0.0000

Data Index: 792664 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1295573 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5635. Min Act: -0.0000

Data Index: 971339 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1160214 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5733. Min Act: -0.0000

Data Index: 616340 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6276. Min Act: -0.0000

Data Index: 210415 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5883. Min Act: -0.0000

Data Index: 823012 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1224765 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5411. Min Act: -0.0000

Data Index: 753674 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5270. Min Act: -0.0000

Data Index: 861433 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5580. Min Act: -0.0000

Data Index: 606594 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5398. Min Act: -0.0000

Data Index: 57342 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5311. Min Act: -0.0000

Data Index: 552478 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5464. Min Act: -0.0000

Data Index: 88800 (C4 (Web Text))

Max Activating Token Index: 510