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

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

Neuron 2000 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: 1.3550. Min Range: -1.3550

Max Act: 1.3550. Min Act: -0.0000

Data Index: 504298 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 1.3550. Min Range: -1.3550

Max Act: 1.2962. Min Act: -0.0000

Data Index: 470519 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.3550. Min Range: -1.3550

Max Act: 1.3300. Min Act: -0.0000

Data Index: 1019030 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 1.3550. Min Range: -1.3550

Max Act: 1.0569. Min Act: -0.0000

Data Index: 553170 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 1.3550. Min Range: -1.3550

Max Act: 1.0262. Min Act: -0.0000

Data Index: 301717 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 1.3550. Min Range: -1.3550

Max Act: 1.0230. Min Act: -0.0000

Data Index: 985124 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9739. Min Act: -0.0000

Data Index: 557859 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1189380 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9316. Min Act: -0.0000

Data Index: 962498 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1193247 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9082. Min Act: 0.0000

Data Index: 410362 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9039. Min Act: -0.0000

Data Index: 688820 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9249. Min Act: -0.0000

Data Index: 87030 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9499. Min Act: -0.0000

Data Index: 897375 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9295. Min Act: -0.0000

Data Index: 137969 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.8995. Min Act: -0.0000

Data Index: 227513 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1019547 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.8595. Min Act: -0.0000

Data Index: 794671 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1292023 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 1.3550. Min Range: -1.3550

Max Act: 0.9112. Min Act: -0.0000

Data Index: 844364 (C4 (Web Text))

Max Activating Token Index: 1011