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

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

Neuron 39 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.6161. Min Act: -0.0000

Data Index: 710696 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.8854. Min Act: -0.0000

Data Index: 332879 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.7651. Min Act: -0.0000

Data Index: 640430 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.5890. Min Act: -0.0000

Data Index: 24547 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.1281. Min Act: -0.0000

Data Index: 239679 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.0252. Min Act: -0.0000

Data Index: 28070 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.0184. Min Act: -0.0000

Data Index: 2466 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 2.8854. Min Range: -2.8854

Max Act: 1.9857. Min Act: -0.0000

Data Index: 1323146 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.0908. Min Act: -0.0000

Data Index: 485225 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 2.8854. Min Range: -2.8854

Max Act: 1.9475. Min Act: -0.0000

Data Index: 506683 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.0367. Min Act: -0.0000

Data Index: 413339 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 2.8854. Min Range: -2.8854

Max Act: 1.9126. Min Act: -0.0000

Data Index: 28879 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.0178. Min Act: -0.0000

Data Index: 1030608 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 2.8854. Min Range: -2.8854

Max Act: 1.8882. Min Act: -0.0000

Data Index: 1077217 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.1270. Min Act: -0.0000

Data Index: 994734 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.0189. Min Act: -0.0000

Data Index: 1086685 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 2.8854. Min Range: -2.8854

Max Act: 1.8540. Min Act: -0.0000

Data Index: 373787 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 2.8854. Min Range: -2.8854

Max Act: 1.9640. Min Act: -0.0000

Data Index: 76595 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.0658. Min Act: -0.0000

Data Index: 780666 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 2.8854. Min Range: -2.8854

Max Act: 1.9643. Min Act: -0.0000

Data Index: 51736 (C4 (Web Text))

Max Activating Token Index: 30