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

Dataset: The Pile

Neuron 1351 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1721437 (The Pile)

Max Activating Token Index: 149

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0622. Min Act: -0.0000

Data Index: 509376 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1494028 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1368014 (The Pile)

Max Activating Token Index: 937

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0566. Min Act: -0.0000

Data Index: 461844 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0520. Min Act: -0.0000

Data Index: 592311 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0453. Min Act: -0.0000

Data Index: 637945 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0508. Min Act: -0.0000

Data Index: 409484 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0490. Min Act: -0.0000

Data Index: 765525 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0555. Min Act: -0.0000

Data Index: 959060 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1803346 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0487. Min Act: -0.0000

Data Index: 517806 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0548. Min Act: -0.0000

Data Index: 741911 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0524. Min Act: -0.0000

Data Index: 80879 (The Pile)

Max Activating Token Index: 909

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1010058 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0528. Min Act: -0.0000

Data Index: 21610 (The Pile)

Max Activating Token Index: 873

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0471. Min Act: -0.0000

Data Index: 509345 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0480. Min Act: -0.0000

Data Index: 461765 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1526203 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1312230 (The Pile)

Max Activating Token Index: 126