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

Dataset: The Pile

Neuron 1890 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: 3.0725. Min Range: -3.0725

Max Act: 3.0725. Min Act: -0.0000

Data Index: 1680918 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.8931. Min Act: -0.0000

Data Index: 1842367 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.8383. Min Act: -0.0000

Data Index: 485311 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.6435. Min Act: -0.0000

Data Index: 539106 (The Pile)

Max Activating Token Index: 816

Text #4

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.7852. Min Act: -0.0000

Data Index: 1266360 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.4921. Min Act: -0.0000

Data Index: 1911426 (The Pile)

Max Activating Token Index: 364

Text #6

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.4043. Min Act: -0.0000

Data Index: 688196 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.2552. Min Act: -0.0001

Data Index: 1931663 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.0605. Min Act: -0.0000

Data Index: 903355 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.8452. Min Act: -0.0000

Data Index: 1824210 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.8365. Min Act: -0.0000

Data Index: 638084 (The Pile)

Max Activating Token Index: 626

Text #11

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.3823. Min Act: -0.0000

Data Index: 896089 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.3484. Min Act: -0.0000

Data Index: 1951486 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.3325. Min Act: -0.0000

Data Index: 1210667 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1007572 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1463955 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.2840. Min Act: -0.0000

Data Index: 871387 (The Pile)

Max Activating Token Index: 845

Text #17

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1596194 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1959263 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1666094 (The Pile)

Max Activating Token Index: 758