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

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

Neuron 891 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0596. Min Act: -0.0002

Data Index: 29790 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1170125 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0553. Min Act: -0.0002

Data Index: 965290 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1255 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0564. Min Act: -0.0002

Data Index: 809610 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1161189 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0531. Min Act: -0.0002

Data Index: 759688 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1119454 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0532. Min Act: -0.0002

Data Index: 848913 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0541. Min Act: -0.0001

Data Index: 893721 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0532. Min Act: -0.0002

Data Index: 332932 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0498. Min Act: -0.0002

Data Index: 349995 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0512. Min Act: -0.0002

Data Index: 557820 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1034198 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0515. Min Act: -0.0002

Data Index: 387627 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0513. Min Act: -0.0002

Data Index: 195684 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0511. Min Act: -0.0002

Data Index: 200761 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0518. Min Act: -0.0002

Data Index: 54453 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0517. Min Act: -0.0002

Data Index: 800169 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0486. Min Act: -0.0002

Data Index: 754834 (C4 (Web Text))

Max Activating Token Index: 916