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

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

Neuron 4734 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1293587 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0640. Min Act: -0.0002

Data Index: 725598 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0656. Min Act: -0.0002

Data Index: 930374 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0682. Min Act: -0.0002

Data Index: 653253 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0557. Min Act: -0.0002

Data Index: 61456 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0607. Min Act: -0.0002

Data Index: 629713 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0618. Min Act: -0.0002

Data Index: 258757 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0563. Min Act: -0.0002

Data Index: 368224 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0580. Min Act: -0.0002

Data Index: 222389 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0574. Min Act: -0.0002

Data Index: 701060 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1206419 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1279638 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0546. Min Act: -0.0002

Data Index: 34096 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1335195 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0552. Min Act: -0.0002

Data Index: 370094 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1107595 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1151416 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0515. Min Act: -0.0002

Data Index: 90757 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1193447 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1121942 (C4 (Web Text))

Max Activating Token Index: 66