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

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

Neuron 52 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5568. Min Range: -5.5568

Max Act: 5.4582. Min Act: -0.0000

Data Index: 454925 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 5.5568. Min Range: -5.5568

Max Act: 5.5568. Min Act: -0.0000

Data Index: 1078524 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 5.5568. Min Range: -5.5568

Max Act: 4.6825. Min Act: -0.0000

Data Index: 300705 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 5.5568. Min Range: -5.5568

Max Act: 4.8701. Min Act: 0.0000

Data Index: 206899 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 5.5568. Min Range: -5.5568

Max Act: 4.2482. Min Act: -0.0000

Data Index: 813432 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 5.5568. Min Range: -5.5568

Max Act: 4.3729. Min Act: 0.0000

Data Index: 31210 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 5.5568. Min Range: -5.5568

Max Act: 4.0337. Min Act: -0.0000

Data Index: 919650 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 5.5568. Min Range: -5.5568

Max Act: 4.2503. Min Act: -0.0000

Data Index: 318128 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 5.5568. Min Range: -5.5568

Max Act: 4.0476. Min Act: -0.0000

Data Index: 140218 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 5.5568. Min Range: -5.5568

Max Act: 3.9941. Min Act: -0.0000

Data Index: 890620 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 5.5568. Min Range: -5.5568

Max Act: 4.1364. Min Act: -0.0000

Data Index: 1241606 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 5.5568. Min Range: -5.5568

Max Act: 3.7674. Min Act: 0.0000

Data Index: 156992 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 5.5568. Min Range: -5.5568

Max Act: 4.0928. Min Act: -0.0000

Data Index: 79319 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 5.5568. Min Range: -5.5568

Max Act: 3.8812. Min Act: -0.0000

Data Index: 301572 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 5.5568. Min Range: -5.5568

Max Act: 3.7397. Min Act: 0.0000

Data Index: 248230 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 5.5568. Min Range: -5.5568

Max Act: 3.5426. Min Act: -0.0000

Data Index: 1129851 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 5.5568. Min Range: -5.5568

Max Act: 3.8135. Min Act: -0.0000

Data Index: 1073021 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 5.5568. Min Range: -5.5568

Max Act: 3.9527. Min Act: 0.0000

Data Index: 828592 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 5.5568. Min Range: -5.5568

Max Act: 3.6702. Min Act: -0.0000

Data Index: 1129243 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 5.5568. Min Range: -5.5568

Max Act: 3.7226. Min Act: -0.0000

Data Index: 1170956 (C4 (Web Text))

Max Activating Token Index: 674