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

Dataset: The Pile

Neuron 3851 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.9421. Min Range: -8.9421

Max Act: 8.9421. Min Act: -0.0000

Data Index: 569301 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 8.9421. Min Range: -8.9421

Max Act: 8.2906. Min Act: -0.0000

Data Index: 669504 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 8.9421. Min Range: -8.9421

Max Act: 8.1765. Min Act: -0.0000

Data Index: 1169995 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 8.9421. Min Range: -8.9421

Max Act: 5.8325. Min Act: -0.0000

Data Index: 832857 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.4634. Min Act: -0.0000

Data Index: 22616 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 8.9421. Min Range: -8.9421

Max Act: 7.4121. Min Act: -0.0000

Data Index: 1941707 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 8.9421. Min Range: -8.9421

Max Act: 7.2010. Min Act: -0.0000

Data Index: 1546295 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.3710. Min Act: -0.0000

Data Index: 1647187 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.2383. Min Act: -0.0000

Data Index: 1317563 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 8.9421. Min Range: -8.9421

Max Act: 7.0123. Min Act: -0.0000

Data Index: 1013250 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.5744. Min Act: -0.0000

Data Index: 1098877 (The Pile)

Max Activating Token Index: 699

Text #11

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.5786. Min Act: -0.0000

Data Index: 833555 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 8.9421. Min Range: -8.9421

Max Act: 5.1103. Min Act: -0.0000

Data Index: 923375 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.5783. Min Act: -0.0000

Data Index: 1961998 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.3683. Min Act: -0.0000

Data Index: 1897458 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.0874. Min Act: -0.0000

Data Index: 84856 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 8.9421. Min Range: -8.9421

Max Act: 5.3332. Min Act: -0.0000

Data Index: 1781761 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.4274. Min Act: -0.0000

Data Index: 624219 (The Pile)

Max Activating Token Index: 666

Text #18

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.4335. Min Act: -0.0000

Data Index: 376548 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 8.9421. Min Range: -8.9421

Max Act: 6.0147. Min Act: -0.0000

Data Index: 1669007 (The Pile)

Max Activating Token Index: 953