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

Dataset: The Pile

Neuron 4680 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0477. Min Range: -1.0477

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1822543 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1576991 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1563575 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4942. Min Act: -0.0000

Data Index: 651543 (The Pile)

Max Activating Token Index: 906

Text #4

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4825. Min Act: -0.0000

Data Index: 969488 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1576734 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1551172 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4502. Min Act: -0.0000

Data Index: 610203 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1027931 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1396886 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.3950. Min Act: -0.0000

Data Index: 929433 (The Pile)

Max Activating Token Index: 140

Text #11

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1958871 (The Pile)

Max Activating Token Index: 328

Text #12

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1109029 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1008181 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1002724 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1970236 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4122. Min Act: -0.0000

Data Index: 136002 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1955824 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1277846 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1808506 (The Pile)

Max Activating Token Index: 320