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

Dataset: The Pile

Neuron 3720 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.9661. Min Act: -0.0000

Data Index: 231066 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 1.0473. Min Range: -1.0473

Max Act: 1.0473. Min Act: -0.0000

Data Index: 659926 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1607317 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.8917. Min Act: -0.0000

Data Index: 190335 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1187333 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.7023. Min Act: -0.0000

Data Index: 481600 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6982. Min Act: -0.0000

Data Index: 518295 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6232. Min Act: -0.0000

Data Index: 980357 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6182. Min Act: -0.0000

Data Index: 971726 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.7677. Min Act: -0.0000

Data Index: 131156 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6388. Min Act: -0.0000

Data Index: 215347 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1419004 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6691. Min Act: -0.0000

Data Index: 88461 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5951. Min Act: -0.0000

Data Index: 354403 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1984240 (The Pile)

Max Activating Token Index: 802

Text #15

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1519326 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6833. Min Act: -0.0000

Data Index: 433722 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5852. Min Act: -0.0000

Data Index: 672595 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.6222. Min Act: -0.0000

Data Index: 294276 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 1.0473. Min Range: -1.0473

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1446243 (The Pile)

Max Activating Token Index: 856