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

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

Neuron 418 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4346. Min Act: -0.0000

Data Index: 357383 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1222299 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4185. Min Act: -0.0000

Data Index: 274626 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4077. Min Act: -0.0000

Data Index: 344460 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3861. Min Act: -0.0000

Data Index: 518979 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4004. Min Act: -0.0000

Data Index: 760540 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3858. Min Act: -0.0000

Data Index: 681469 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3806. Min Act: -0.0000

Data Index: 640518 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3707. Min Act: -0.0000

Data Index: 85622 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3715. Min Act: -0.0000

Data Index: 150539 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1501603 (Python Code)

Max Activating Token Index: 866

Text #11

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3610. Min Act: -0.0000

Data Index: 262812 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3701. Min Act: -0.0000

Data Index: 784554 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1599983 (Python Code)

Max Activating Token Index: 686

Text #14

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3583. Min Act: -0.0000

Data Index: 30254 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3524. Min Act: -0.0000

Data Index: 994110 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3352. Min Act: -0.0000

Data Index: 471566 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3259. Min Act: -0.0000

Data Index: 473735 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3305. Min Act: -0.0000

Data Index: 752060 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3197. Min Act: -0.0000

Data Index: 223269 (C4 (Web Text))

Max Activating Token Index: 246