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

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

Neuron 979 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0660. Min Act: -0.0005

Data Index: 353102 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0656. Min Act: -0.0005

Data Index: 683366 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0662. Min Act: -0.0005

Data Index: 1092349 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0005

Data Index: 315155 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0653. Min Act: -0.0005

Data Index: 1288677 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0607. Min Act: -0.0005

Data Index: 141757 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0620. Min Act: -0.0005

Data Index: 1250340 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0607. Min Act: -0.0005

Data Index: 65482 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0620. Min Act: -0.0005

Data Index: 636194 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0605. Min Act: -0.0005

Data Index: 510178 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0602. Min Act: -0.0005

Data Index: 665012 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0585. Min Act: -0.0005

Data Index: 1327874 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0598. Min Act: -0.0005

Data Index: 490003 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0593. Min Act: -0.0005

Data Index: 575318 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0565. Min Act: -0.0005

Data Index: 1328640 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0581. Min Act: -0.0005

Data Index: 208555 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0588. Min Act: -0.0005

Data Index: 1338551 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0572. Min Act: -0.0005

Data Index: 1359203 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0539. Min Act: -0.0005

Data Index: 1112662 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0562. Min Act: -0.0005

Data Index: 533440 (C4 (Web Text))

Max Activating Token Index: 212