Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3131 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0665. Min Range: -1.0665

Max Act: 1.0665. Min Act: -0.0002

Data Index: 512485 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.9654. Min Act: -0.0002

Data Index: 413453 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.9603. Min Act: -0.0001

Data Index: 76989 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.9521. Min Act: -0.0002

Data Index: 610218 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.9167. Min Act: -0.0002

Data Index: 106033 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.8241. Min Act: -0.0001

Data Index: 113925 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.8762. Min Act: -0.0001

Data Index: 175329 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.8185. Min Act: -0.0002

Data Index: 27046 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.8103. Min Act: -0.0002

Data Index: 723816 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.8611. Min Act: -0.0002

Data Index: 342040 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.8607. Min Act: -0.0001

Data Index: 871271 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.8168. Min Act: -0.0001

Data Index: 356475 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.7827. Min Act: -0.0002

Data Index: 591196 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.7044. Min Act: -0.0002

Data Index: 934444 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.8675. Min Act: -0.0002

Data Index: 685850 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.8148. Min Act: -0.0002

Data Index: 680048 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.7676. Min Act: -0.0002

Data Index: 1353698 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.7825. Min Act: -0.0001

Data Index: 1323531 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.7384. Min Act: -0.0002

Data Index: 833938 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.0665. Min Range: -1.0665

Max Act: 0.7801. Min Act: -0.0001

Data Index: 276102 (C4 (Web Text))

Max Activating Token Index: 124