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

Dataset: The Pile

Neuron 936 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7907. Min Act: -0.0000

Data Index: 961889 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7949. Min Act: -0.0000

Data Index: 718111 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6848. Min Act: -0.0000

Data Index: 857402 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1598546 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5655. Min Act: -0.0000

Data Index: 77979 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5815. Min Act: -0.0000

Data Index: 862515 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1391218 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1156118 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1840128 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6092. Min Act: -0.0000

Data Index: 922541 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5522. Min Act: -0.0000

Data Index: 781847 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5813. Min Act: -0.0000

Data Index: 301350 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5782. Min Act: -0.0000

Data Index: 107306 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5604. Min Act: -0.0000

Data Index: 815335 (The Pile)

Max Activating Token Index: 743

Text #14

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1021551 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1579939 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1675237 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5407. Min Act: -0.0000

Data Index: 29672 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1084820 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5529. Min Act: -0.0000

Data Index: 601665 (The Pile)

Max Activating Token Index: 395