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

Dataset: The Pile

Neuron 1221 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: 0.6788. Min Range: -0.6788

Max Act: 0.6788. Min Act: -0.0000

Data Index: 461208 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6390. Min Act: -0.0000

Data Index: 58053 (The Pile)

Max Activating Token Index: 771

Text #2

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5755. Min Act: -0.0000

Data Index: 700592 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1969918 (The Pile)

Max Activating Token Index: 316

Text #4

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5850. Min Act: -0.0001

Data Index: 1819848 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1643814 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1049197 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1133302 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5469. Min Act: -0.0000

Data Index: 249407 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1035487 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5041. Min Act: -0.0000

Data Index: 913171 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1749443 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1667047 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4927. Min Act: -0.0000

Data Index: 652974 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1646568 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5214. Min Act: -0.0000

Data Index: 34158 (The Pile)

Max Activating Token Index: 899

Text #16

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4809. Min Act: -0.0000

Data Index: 269103 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4682. Min Act: -0.0000

Data Index: 626822 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1141307 (The Pile)

Max Activating Token Index: 914

Text #19

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1300059 (The Pile)

Max Activating Token Index: 83