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

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

Neuron 261 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: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0002

Data Index: 475308 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0751. Min Act: -0.0002

Data Index: 816696 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0771. Min Act: -0.0002

Data Index: 482749 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1061591 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0652. Min Act: -0.0002

Data Index: 885846 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0644. Min Act: -0.0002

Data Index: 111790 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1222628 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0619. Min Act: -0.0002

Data Index: 688397 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0616. Min Act: -0.0002

Data Index: 335589 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0610. Min Act: -0.0002

Data Index: 560498 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0589. Min Act: -0.0002

Data Index: 349479 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1220695 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0585. Min Act: -0.0002

Data Index: 632544 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1014821 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1162838 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0555. Min Act: -0.0002

Data Index: 593188 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1310644 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0552. Min Act: -0.0002

Data Index: 771977 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1128697 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0550. Min Act: -0.0002

Data Index: 719809 (C4 (Web Text))

Max Activating Token Index: 608