Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 993 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.2320. Min Range: -3.2320

Max Act: 3.1241. Min Act: -0.0000

Data Index: 171734 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 3.2320. Min Range: -3.2320

Max Act: 3.1998. Min Act: -0.0000

Data Index: 343496 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 3.2320. Min Range: -3.2320

Max Act: 3.0483. Min Act: 0.0000

Data Index: 472267 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 3.2320. Min Range: -3.2320

Max Act: 3.1250. Min Act: -0.0000

Data Index: 658339 (The Pile)

Max Activating Token Index: 381

Text #4

Max Range: 3.2320. Min Range: -3.2320

Max Act: 3.2320. Min Act: -0.0000

Data Index: 1594448 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 3.2320. Min Range: -3.2320

Max Act: 3.0954. Min Act: 0.0000

Data Index: 960922 (The Pile)

Max Activating Token Index: 37

Text #6

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.9109. Min Act: -0.0000

Data Index: 973020 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 3.2320. Min Range: -3.2320

Max Act: 3.0288. Min Act: -0.0000

Data Index: 187032 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.8589. Min Act: -0.0000

Data Index: 940844 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 3.2320. Min Range: -3.2320

Max Act: 3.0036. Min Act: -0.0000

Data Index: 1467949 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.7427. Min Act: 0.0000

Data Index: 1369283 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.9795. Min Act: -0.0000

Data Index: 1411806 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.8302. Min Act: -0.0000

Data Index: 613807 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.9590. Min Act: -0.0000

Data Index: 1242933 (The Pile)

Max Activating Token Index: 733

Text #14

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.6733. Min Act: -0.0000

Data Index: 120318 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.7934. Min Act: 0.0000

Data Index: 215580 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.9513. Min Act: -0.0000

Data Index: 1192890 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.7889. Min Act: 0.0000

Data Index: 1928909 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.9364. Min Act: -0.0000

Data Index: 114973 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.6429. Min Act: 0.0000

Data Index: 574762 (The Pile)

Max Activating Token Index: 143