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

Dataset: The Pile

Neuron 532 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4510. Min Range: -5.4510

Max Act: 5.4510. Min Act: -0.0000

Data Index: 1391361 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 5.4510. Min Range: -5.4510

Max Act: 5.4138. Min Act: -0.0000

Data Index: 491774 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 5.4510. Min Range: -5.4510

Max Act: 5.0356. Min Act: -0.0000

Data Index: 84408 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.7252. Min Act: -0.0000

Data Index: 1923195 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.6950. Min Act: -0.0000

Data Index: 931691 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.5144. Min Act: -0.0000

Data Index: 1200454 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.6432. Min Act: -0.0000

Data Index: 1747895 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.8175. Min Act: -0.0000

Data Index: 1805967 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.5797. Min Act: -0.0000

Data Index: 1349815 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.7613. Min Act: -0.0000

Data Index: 1657954 (The Pile)

Max Activating Token Index: 845

Text #10

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.4391. Min Act: -0.0000

Data Index: 482609 (The Pile)

Max Activating Token Index: 706

Text #11

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.3751. Min Act: -0.0000

Data Index: 1011250 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.3662. Min Act: -0.0000

Data Index: 632507 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.4860. Min Act: -0.0000

Data Index: 1854527 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.2818. Min Act: -0.0000

Data Index: 1874674 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.3022. Min Act: -0.0000

Data Index: 173855 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.0073. Min Act: -0.0000

Data Index: 1582777 (The Pile)

Max Activating Token Index: 317

Text #17

Max Range: 5.4510. Min Range: -5.4510

Max Act: 4.1502. Min Act: -0.0000

Data Index: 1846704 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 5.4510. Min Range: -5.4510

Max Act: 3.9745. Min Act: -0.0000

Data Index: 414159 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 5.4510. Min Range: -5.4510

Max Act: 3.9575. Min Act: -0.0000

Data Index: 1841970 (The Pile)

Max Activating Token Index: 416