Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 733 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0582. Min Act: -0.0004

Data Index: 1107149 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0627. Min Act: -0.0004

Data Index: 775472 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0556. Min Act: -0.0004

Data Index: 684360 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0557. Min Act: -0.0004

Data Index: 268382 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0618. Min Act: -0.0004

Data Index: 706827 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0542. Min Act: -0.0004

Data Index: 915171 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0588. Min Act: -0.0004

Data Index: 189648 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0549. Min Act: -0.0004

Data Index: 962712 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0589. Min Act: -0.0004

Data Index: 1034450 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0592. Min Act: -0.0004

Data Index: 594038 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0588. Min Act: -0.0004

Data Index: 37284 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0580. Min Act: -0.0004

Data Index: 699723 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0533. Min Act: -0.0004

Data Index: 225185 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0599. Min Act: -0.0004

Data Index: 384931 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0576. Min Act: -0.0004

Data Index: 312889 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0572. Min Act: -0.0004

Data Index: 1135893 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0541. Min Act: -0.0004

Data Index: 988129 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0544. Min Act: -0.0004

Data Index: 889503 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0517. Min Act: -0.0004

Data Index: 368897 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0564. Min Act: -0.0004

Data Index: 981139 (C4 (Web Text))

Max Activating Token Index: 1023