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

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

Neuron 4777 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: 1.3059. Min Range: -1.3059

Max Act: 1.2707. Min Act: -0.0000

Data Index: 790168 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.2565. Min Act: -0.0000

Data Index: 787567 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.3059. Min Act: -0.0000

Data Index: 91691 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1783. Min Act: -0.0000

Data Index: 152926 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1279. Min Act: -0.0000

Data Index: 730991 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1230. Min Act: -0.0000

Data Index: 448354 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1841. Min Act: -0.0000

Data Index: 653973 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0994. Min Act: -0.0000

Data Index: 753150 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1683. Min Act: -0.0000

Data Index: 868747 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0734. Min Act: -0.0000

Data Index: 569595 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 1.3059. Min Range: -1.3059

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1340851 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1187. Min Act: -0.0000

Data Index: 575664 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1340948 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0319. Min Act: -0.0000

Data Index: 377055 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0299. Min Act: -0.0000

Data Index: 15594 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.3059. Min Range: -1.3059

Max Act: 0.9898. Min Act: -0.0000

Data Index: 914441 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 1.3059. Min Range: -1.3059

Max Act: 0.9993. Min Act: -0.0000

Data Index: 750596 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 1.3059. Min Range: -1.3059

Max Act: 0.9977. Min Act: -0.0000

Data Index: 39048 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0623. Min Act: -0.0000

Data Index: 95272 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0433. Min Act: -0.0000

Data Index: 315285 (C4 (Web Text))

Max Activating Token Index: 135