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

Dataset: The Pile

Neuron 3913 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1478460 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1855384 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1235330 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1525364 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1629874 (The Pile)

Max Activating Token Index: 137

Text #5

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3053. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1399521 (The Pile)

Max Activating Token Index: 415

Text #7

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1296437 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2986. Min Act: -0.0000

Data Index: 660272 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2825. Min Act: -0.0000

Data Index: 719114 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2941. Min Act: -0.0000

Data Index: 238208 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2899. Min Act: -0.0000

Data Index: 957913 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2975. Min Act: -0.0000

Data Index: 150332 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3000. Min Act: -0.0000

Data Index: 860673 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2755. Min Act: -0.0000

Data Index: 562987 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1575621 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1089665 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2678. Min Act: -0.0000

Data Index: 882326 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2621. Min Act: -0.0000

Data Index: 158682 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1967984 (The Pile)

Max Activating Token Index: 482