Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1324 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.8579. Min Act: -0.0001

Data Index: 9234 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.2591. Min Act: -0.0001

Data Index: 35934 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.2414. Min Act: -0.0001

Data Index: 452046 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.1636. Min Act: -0.0001

Data Index: 359446 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.2320. Min Act: -0.0001

Data Index: 735865 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.1848. Min Act: -0.0001

Data Index: 787730 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.1532. Min Act: -0.0001

Data Index: 595719 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.1288. Min Act: -0.0001

Data Index: 369054 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.1090. Min Act: -0.0001

Data Index: 1143884 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.0377. Min Act: -0.0001

Data Index: 570562 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.1063. Min Act: -0.0001

Data Index: 1076886 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.0860. Min Act: -0.0001

Data Index: 1108659 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.0123. Min Act: -0.0001

Data Index: 813852 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.0768. Min Act: -0.0001

Data Index: 1304602 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.1249. Min Act: -0.0001

Data Index: 1141093 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.0513. Min Act: -0.0001

Data Index: 588008 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.0465. Min Act: -0.0001

Data Index: 327625 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.0511. Min Act: -0.0001

Data Index: 960696 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.8579. Min Range: -1.8579

Max Act: 0.9897. Min Act: -0.0001

Data Index: 180526 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.8579. Min Range: -1.8579

Max Act: 1.0871. Min Act: -0.0001

Data Index: 454418 (C4 (Web Text))

Max Activating Token Index: 835