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

Dataset: The Pile

Neuron 4836 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1989. Min Range: -3.1989

Max Act: 3.1989. Min Act: -0.0000

Data Index: 276128 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.7007. Min Act: -0.0000

Data Index: 923182 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.7901. Min Act: -0.0000

Data Index: 1050990 (The Pile)

Max Activating Token Index: 148

Text #3

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.5359. Min Act: -0.0000

Data Index: 555241 (The Pile)

Max Activating Token Index: 736

Text #4

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.6111. Min Act: -0.0000

Data Index: 988023 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.4630. Min Act: -0.0000

Data Index: 1558637 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.5343. Min Act: -0.0000

Data Index: 885279 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.4015. Min Act: -0.0000

Data Index: 1371110 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.3971. Min Act: -0.0000

Data Index: 898743 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.5245. Min Act: -0.0000

Data Index: 410821 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.3683. Min Act: -0.0000

Data Index: 195878 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.3299. Min Act: -0.0000

Data Index: 1718613 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.3357. Min Act: -0.0000

Data Index: 1981603 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.2989. Min Act: -0.0000

Data Index: 1456394 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.2816. Min Act: -0.0000

Data Index: 1374125 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.1431. Min Act: -0.0000

Data Index: 8142 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.2699. Min Act: -0.0000

Data Index: 716475 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.2469. Min Act: -0.0000

Data Index: 760535 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.1340. Min Act: -0.0000

Data Index: 1916550 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.2231. Min Act: -0.0000

Data Index: 285154 (The Pile)

Max Activating Token Index: 527