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

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

Neuron 2811 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0954. Min Range: -1.0954

Max Act: 1.0954. Min Act: -0.0000

Data Index: 820971 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.9644. Min Act: -0.0000

Data Index: 295389 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.8217. Min Act: -0.0000

Data Index: 995620 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7168. Min Act: -0.0000

Data Index: 444106 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7079. Min Act: -0.0000

Data Index: 972540 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7111. Min Act: 0.0000

Data Index: 722553 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1059596 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7006. Min Act: -0.0000

Data Index: 557796 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7423. Min Act: -0.0000

Data Index: 587270 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1208575 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1004181 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1038370 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1238927 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1156633 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1627748 (Python Code)

Max Activating Token Index: 553

Text #15

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1314212 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.6286. Min Act: -0.0000

Data Index: 531583 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1078268 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.6212. Min Act: -0.0000

Data Index: 842558 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1123718 (C4 (Web Text))

Max Activating Token Index: 443