Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2347 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.4605. Min Act: -0.0000

Data Index: 303601 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.5659. Min Act: -0.0000

Data Index: 158818 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.6595. Min Act: -0.0000

Data Index: 892575 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.5408. Min Act: -0.0000

Data Index: 339003 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.2666. Min Act: -0.0000

Data Index: 447969 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.3383. Min Act: -0.0000

Data Index: 483233 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.2978. Min Act: -0.0000

Data Index: 110007 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.2728. Min Act: -0.0000

Data Index: 337625 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.1073. Min Act: -0.0000

Data Index: 89801 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.0868. Min Act: -0.0000

Data Index: 223993 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.0844. Min Act: -0.0000

Data Index: 455144 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.0774. Min Act: -0.0000

Data Index: 53351 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.1438. Min Act: -0.0000

Data Index: 915703 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.0707. Min Act: -0.0000

Data Index: 1069268 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.0600. Min Act: -0.0000

Data Index: 444593 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.0870. Min Act: -0.0000

Data Index: 1280611 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 2.4605. Min Range: -2.4605

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1047751 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 2.4605. Min Range: -2.4605

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1132545 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.0615. Min Act: -0.0000

Data Index: 1273462 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1035736 (C4 (Web Text))

Max Activating Token Index: 49