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

Dataset: The Pile

Neuron 4059 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1544020 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4624. Min Act: -0.0000

Data Index: 356504 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4229. Min Act: -0.0000

Data Index: 730386 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4479. Min Act: -0.0000

Data Index: 243970 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4237. Min Act: -0.0000

Data Index: 788332 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1710683 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3825. Min Act: -0.0000

Data Index: 276262 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3676. Min Act: -0.0000

Data Index: 541422 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3761. Min Act: -0.0000

Data Index: 130870 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3737. Min Act: -0.0000

Data Index: 447201 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1703556 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3766. Min Act: -0.0000

Data Index: 316468 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1841035 (The Pile)

Max Activating Token Index: 525

Text #13

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3706. Min Act: -0.0000

Data Index: 546862 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3624. Min Act: -0.0000

Data Index: 715740 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1316207 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3487. Min Act: -0.0000

Data Index: 937023 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3579. Min Act: -0.0000

Data Index: 662706 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3629. Min Act: -0.0000

Data Index: 253323 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3463. Min Act: -0.0000

Data Index: 315493 (The Pile)

Max Activating Token Index: 63