Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3863 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0401. Min Range: -1.0401

Max Act: 1.0401. Min Act: -0.0000

Data Index: 83858 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 1.0401. Min Range: -1.0401

Max Act: 1.0362. Min Act: -0.0000

Data Index: 475441 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.9427. Min Act: -0.0000

Data Index: 816940 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1516443 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1826586 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.9343. Min Act: -0.0000

Data Index: 959970 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1596624 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1169088 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8909. Min Act: -0.0000

Data Index: 282333 (The Pile)

Max Activating Token Index: 15

Text #9

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1241848 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8821. Min Act: -0.0000

Data Index: 539896 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8297. Min Act: -0.0000

Data Index: 429836 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8636. Min Act: -0.0000

Data Index: 64347 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1416117 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8686. Min Act: -0.0000

Data Index: 195280 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1109627 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8570. Min Act: -0.0000

Data Index: 485878 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1634023 (The Pile)

Max Activating Token Index: 428

Text #18

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8582. Min Act: -0.0000

Data Index: 494790 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8432. Min Act: -0.0000

Data Index: 794726 (The Pile)

Max Activating Token Index: 7