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

Dataset: The Pile

Neuron 3897 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5965. Min Range: -5.5965

Max Act: 5.5965. Min Act: -0.0000

Data Index: 1650859 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 5.5965. Min Range: -5.5965

Max Act: 5.2722. Min Act: -0.0000

Data Index: 919758 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 5.5965. Min Range: -5.5965

Max Act: 5.0293. Min Act: -0.0000

Data Index: 1141579 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 5.5965. Min Range: -5.5965

Max Act: 5.2013. Min Act: -0.0000

Data Index: 612716 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 5.5965. Min Range: -5.5965

Max Act: 5.0903. Min Act: 0.0001

Data Index: 1865226 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.8765. Min Act: -0.0000

Data Index: 1587121 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.8823. Min Act: -0.0000

Data Index: 1164127 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 5.5965. Min Range: -5.5965

Max Act: 5.0738. Min Act: -0.0000

Data Index: 893696 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.9145. Min Act: -0.0000

Data Index: 1441946 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.7493. Min Act: -0.0000

Data Index: 1798404 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.3909. Min Act: -0.0000

Data Index: 377 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.8011. Min Act: 0.0002

Data Index: 1543975 (The Pile)

Max Activating Token Index: 965

Text #12

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.7649. Min Act: -0.0000

Data Index: 522071 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.9186. Min Act: 0.0002

Data Index: 843501 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.3322. Min Act: -0.0000

Data Index: 187990 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.3503. Min Act: -0.0000

Data Index: 65749 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.7391. Min Act: -0.0000

Data Index: 1635415 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.4435. Min Act: 0.0000

Data Index: 1163625 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.1394. Min Act: -0.0000

Data Index: 577075 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 5.5965. Min Range: -5.5965

Max Act: 4.4287. Min Act: -0.0000

Data Index: 1703502 (The Pile)

Max Activating Token Index: 370