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

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

Neuron 5100 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2639. Min Range: -2.2639

Max Act: 2.2639. Min Act: -0.0000

Data Index: 646349 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 2.2639. Min Range: -2.2639

Max Act: 2.1451. Min Act: -0.0001

Data Index: 286625 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.9189. Min Act: -0.0000

Data Index: 168692 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 2.2639. Min Range: -2.2639

Max Act: 2.1337. Min Act: -0.0000

Data Index: 263794 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.9988. Min Act: -0.0001

Data Index: 497663 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 2.2639. Min Range: -2.2639

Max Act: 2.0631. Min Act: -0.0001

Data Index: 299942 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.9283. Min Act: -0.0001

Data Index: 556893 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.9493. Min Act: -0.0000

Data Index: 1104825 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 2.2639. Min Range: -2.2639

Max Act: 2.0353. Min Act: -0.0000

Data Index: 848847 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 2.2639. Min Range: -2.2639

Max Act: 2.0263. Min Act: -0.0000

Data Index: 146835 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.9785. Min Act: -0.0001

Data Index: 983029 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.7497. Min Act: -0.0000

Data Index: 187102 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.9283. Min Act: -0.0000

Data Index: 526197 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.9779. Min Act: -0.0000

Data Index: 706986 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 2.2639. Min Range: -2.2639

Max Act: 2.0021. Min Act: -0.0000

Data Index: 737945 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.9128. Min Act: -0.0001

Data Index: 6847 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.9207. Min Act: -0.0000

Data Index: 725009 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.8056. Min Act: -0.0001

Data Index: 1020263 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.4236. Min Act: -0.0000

Data Index: 588039 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 2.2639. Min Range: -2.2639

Max Act: 1.8211. Min Act: -0.0001

Data Index: 816001 (C4 (Web Text))

Max Activating Token Index: 987