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

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

Neuron 3892 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: 1.3624. Min Range: -1.3624

Max Act: 1.3624. Min Act: -0.0000

Data Index: 716319 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.2688. Min Act: -0.0000

Data Index: 479743 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.1844. Min Act: -0.0000

Data Index: 924247 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1009398 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0631. Min Act: -0.0000

Data Index: 720514 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.1695. Min Act: -0.0000

Data Index: 296723 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0798. Min Act: -0.0000

Data Index: 951578 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1292217 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9689. Min Act: -0.0000

Data Index: 842800 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1231518 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9912. Min Act: -0.0000

Data Index: 184623 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0059. Min Act: -0.0000

Data Index: 867889 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1164387 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8753. Min Act: -0.0000

Data Index: 75150 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9486. Min Act: -0.0000

Data Index: 919556 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1329446 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8241. Min Act: -0.0000

Data Index: 67936 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8719. Min Act: 0.0000

Data Index: 623642 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1131293 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1144357 (C4 (Web Text))

Max Activating Token Index: 245