Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3873 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.8568. Min Act: -0.0000

Data Index: 997175 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.3857. Min Act: -0.0000

Data Index: 485120 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.3654. Min Act: -0.0000

Data Index: 388260 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.1774. Min Act: -0.0000

Data Index: 691816 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.1790. Min Act: -0.0000

Data Index: 935751 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1030045 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.0502. Min Act: -0.0000

Data Index: 942565 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.0636. Min Act: -0.0000

Data Index: 199868 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.0011. Min Act: -0.0000

Data Index: 387077 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.8568. Min Range: -1.8568

Max Act: 1.0048. Min Act: -0.0000

Data Index: 489592 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9631. Min Act: -0.0000

Data Index: 435191 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9611. Min Act: -0.0000

Data Index: 526946 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1094688 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1179363 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1076646 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9298. Min Act: -0.0000

Data Index: 532418 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1105710 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9373. Min Act: -0.0000

Data Index: 659752 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1149800 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 1.8568. Min Range: -1.8568

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1111950 (C4 (Web Text))

Max Activating Token Index: 20