Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3459 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1046402 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0733. Min Act: -0.0000

Data Index: 72167 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0601. Min Act: -0.0000

Data Index: 701457 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0556. Min Act: -0.0000

Data Index: 868548 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1332304 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0562. Min Act: -0.0000

Data Index: 892468 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0524. Min Act: -0.0000

Data Index: 823094 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0579. Min Act: -0.0000

Data Index: 217427 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0550. Min Act: -0.0000

Data Index: 670020 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1216101 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0532. Min Act: -0.0000

Data Index: 925381 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0615. Min Act: -0.0000

Data Index: 790081 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0509. Min Act: -0.0000

Data Index: 364680 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1326640 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0547. Min Act: -0.0000

Data Index: 1071661 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0487. Min Act: -0.0000

Data Index: 334340 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1099700 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0523. Min Act: -0.0000

Data Index: 539513 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1254164 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1349923 (C4 (Web Text))

Max Activating Token Index: 365