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

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

Neuron 3273 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3625. Min Range: -3.3625

Max Act: 3.3625. Min Act: -0.0000

Data Index: 825723 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 3.3625. Min Range: -3.3625

Max Act: 3.0769. Min Act: -0.0000

Data Index: 583736 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 3.3625. Min Range: -3.3625

Max Act: 3.0314. Min Act: -0.0000

Data Index: 792693 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 3.3625. Min Range: -3.3625

Max Act: 3.1698. Min Act: -0.0000

Data Index: 384487 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.9969. Min Act: -0.0000

Data Index: 906076 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.8086. Min Act: -0.0000

Data Index: 159828 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.8880. Min Act: -0.0000

Data Index: 872559 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 3.3625. Min Range: -3.3625

Max Act: 3.0173. Min Act: -0.0000

Data Index: 697004 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.8484. Min Act: -0.0000

Data Index: 66310 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.8692. Min Act: -0.0000

Data Index: 899822 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 3.3625. Min Range: -3.3625

Max Act: 3.0023. Min Act: -0.0000

Data Index: 1009857 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.6775. Min Act: -0.0000

Data Index: 906691 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.8316. Min Act: -0.0000

Data Index: 1357940 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.7933. Min Act: -0.0000

Data Index: 752607 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.6364. Min Act: -0.0000

Data Index: 1311176 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.7633. Min Act: -0.0000

Data Index: 877203 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.6984. Min Act: -0.0000

Data Index: 765973 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.7208. Min Act: -0.0000

Data Index: 1060806 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.8572. Min Act: -0.0000

Data Index: 1059979 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 3.3625. Min Range: -3.3625

Max Act: 2.6763. Min Act: -0.0000

Data Index: 733334 (C4 (Web Text))

Max Activating Token Index: 913