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

Dataset: The Pile

Neuron 590 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: 0.3614. Min Range: -0.3614

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1679409 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3075. Min Act: -0.0000

Data Index: 443063 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2735. Min Act: -0.0000

Data Index: 480152 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1094184 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2785. Min Act: -0.0000

Data Index: 425531 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2635. Min Act: -0.0000

Data Index: 199614 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1943826 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1288780 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2563. Min Act: -0.0000

Data Index: 925066 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2667. Min Act: -0.0000

Data Index: 177000 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1680653 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1183298 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1473346 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2527. Min Act: -0.0000

Data Index: 203667 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2566. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2502. Min Act: -0.0000

Data Index: 244882 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2676. Min Act: -0.0000

Data Index: 736979 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1082601 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2487. Min Act: -0.0000

Data Index: 34970 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2476. Min Act: -0.0000

Data Index: 874411 (The Pile)

Max Activating Token Index: 449