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

Dataset: The Pile

Neuron 1813 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: 1.5129. Min Range: -1.5129

Max Act: 1.4414. Min Act: -0.0000

Data Index: 375519 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.5129. Min Act: -0.0000

Data Index: 1001496 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.5009. Min Act: -0.0000

Data Index: 526354 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3952. Min Act: -0.0000

Data Index: 1166153 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3942. Min Act: -0.0000

Data Index: 780514 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.5024. Min Act: -0.0000

Data Index: 568531 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2696. Min Act: -0.0000

Data Index: 1853818 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1074948 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3827. Min Act: -0.0000

Data Index: 523360 (The Pile)

Max Activating Token Index: 773

Text #9

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3717. Min Act: -0.0000

Data Index: 1226333 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3034. Min Act: -0.0000

Data Index: 61364 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1584752 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1272178 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3535. Min Act: -0.0000

Data Index: 1823422 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3359. Min Act: -0.0000

Data Index: 790785 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3979. Min Act: -0.0000

Data Index: 356772 (The Pile)

Max Activating Token Index: 914

Text #16

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.3469. Min Act: -0.0000

Data Index: 516094 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.4677. Min Act: -0.0000

Data Index: 1766898 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2318. Min Act: -0.0000

Data Index: 1390625 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1934027 (The Pile)

Max Activating Token Index: 640