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

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

Neuron 2770 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6873. Min Act: -0.0000

Data Index: 1477795 (Python Code)

Max Activating Token Index: 645

Text #1

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1447723 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1649229 (Python Code)

Max Activating Token Index: 92

Text #3

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1573675 (Python Code)

Max Activating Token Index: 340

Text #4

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1428331 (Python Code)

Max Activating Token Index: 535

Text #5

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1651041 (Python Code)

Max Activating Token Index: 563

Text #6

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1646478 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1025262 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1390816 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1484444 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1493876 (Python Code)

Max Activating Token Index: 583

Text #11

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1278235 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1493860 (Python Code)

Max Activating Token Index: 343

Text #13

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4804. Min Act: -0.0000

Data Index: 577639 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1359152 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1511489 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1164474 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1466425 (Python Code)

Max Activating Token Index: 964

Text #18

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1371405 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1440614 (Python Code)

Max Activating Token Index: 111