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

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

Neuron 2200 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: 4.0537. Min Range: -4.0537

Max Act: 4.0537. Min Act: -0.0000

Data Index: 837552 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.6689. Min Act: -0.0000

Data Index: 1100452 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.0776. Min Act: -0.0000

Data Index: 702865 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.0270. Min Act: -0.0000

Data Index: 530681 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.3531. Min Act: -0.0000

Data Index: 578149 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.0489. Min Act: -0.0000

Data Index: 899794 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.0092. Min Act: -0.0000

Data Index: 536809 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.8625. Min Act: -0.0000

Data Index: 391798 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.9739. Min Act: -0.0000

Data Index: 1125695 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.9323. Min Act: -0.0000

Data Index: 272953 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.8088. Min Act: -0.0000

Data Index: 1267063 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.9013. Min Act: -0.0000

Data Index: 12791 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.7597. Min Act: -0.0000

Data Index: 1145141 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.0195. Min Act: -0.0000

Data Index: 15012 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.8689. Min Act: -0.0000

Data Index: 828173 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.1224. Min Act: -0.0000

Data Index: 1180251 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.6833. Min Act: -0.0000

Data Index: 680623 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.9346. Min Act: -0.0000

Data Index: 699836 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.8043. Min Act: -0.0000

Data Index: 308889 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.7898. Min Act: -0.0000

Data Index: 703702 (C4 (Web Text))

Max Activating Token Index: 545