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

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

Neuron 4635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.6678. Min Act: -0.0000

Data Index: 10893 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.4484. Min Act: -0.0000

Data Index: 771299 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.5480. Min Act: -0.0000

Data Index: 526327 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.4818. Min Act: -0.0000

Data Index: 1043163 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.3448. Min Act: -0.0000

Data Index: 769540 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.3284. Min Act: -0.0000

Data Index: 315729 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.2716. Min Act: -0.0000

Data Index: 1060076 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.2631. Min Act: -0.0000

Data Index: 486623 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.1528. Min Act: -0.0000

Data Index: 249060 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.1195. Min Act: -0.0000

Data Index: 772760 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1203253 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.1162. Min Act: -0.0000

Data Index: 10946 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.1062. Min Act: -0.0000

Data Index: 220119 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.2062. Min Act: -0.0000

Data Index: 1138929 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 1.6678. Min Range: -1.6678

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1008584 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1100534 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.0735. Min Act: -0.0000

Data Index: 798204 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1109792 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.0390. Min Act: -0.0000

Data Index: 559475 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.6678. Min Range: -1.6678

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1253552 (C4 (Web Text))

Max Activating Token Index: 37