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

Dataset: The Pile

Neuron 2521 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: 1.5796. Min Range: -1.5796

Max Act: 1.5796. Min Act: -0.0000

Data Index: 1437997 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1751734 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.0626. Min Act: -0.0000

Data Index: 50638 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.0903. Min Act: -0.0000

Data Index: 143623 (The Pile)

Max Activating Token Index: 870

Text #4

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1482854 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1829795 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.9307. Min Act: -0.0000

Data Index: 125193 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.9193. Min Act: -0.0000

Data Index: 35964 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.9221. Min Act: -0.0000

Data Index: 738772 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.9108. Min Act: -0.0000

Data Index: 422891 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.9260. Min Act: -0.0000

Data Index: 171610 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.8595. Min Act: -0.0000

Data Index: 751834 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.8475. Min Act: -0.0000

Data Index: 889455 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.8457. Min Act: -0.0000

Data Index: 529075 (The Pile)

Max Activating Token Index: 927

Text #14

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.8635. Min Act: -0.0000

Data Index: 786889 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1314449 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1765218 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.7700. Min Act: -0.0000

Data Index: 169159 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.8367. Min Act: -0.0000

Data Index: 231322 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 1.5796. Min Range: -1.5796

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1452201 (The Pile)

Max Activating Token Index: 290