Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1825 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0765. Min Act: -0.0002

Data Index: 999044 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0736. Min Act: -0.0001

Data Index: 80192 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0728. Min Act: -0.0002

Data Index: 958088 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0721. Min Act: -0.0002

Data Index: 544708 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0710. Min Act: -0.0001

Data Index: 890938 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0695. Min Act: -0.0002

Data Index: 30253 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1157085 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1256826 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1021796 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0614. Min Act: -0.0002

Data Index: 465078 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1190460 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0627. Min Act: -0.0002

Data Index: 549143 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1089486 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0594. Min Act: -0.0002

Data Index: 872909 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0575. Min Act: -0.0002

Data Index: 617269 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0583. Min Act: -0.0002

Data Index: 729523 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0585. Min Act: -0.0002

Data Index: 963847 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0568. Min Act: -0.0002

Data Index: 699222 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1086794 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0558. Min Act: -0.0002

Data Index: 844631 (C4 (Web Text))

Max Activating Token Index: 868