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

Dataset: The Pile

Neuron 4057 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: 0.9221. Min Range: -0.9221

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1254563 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1141659 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.9221. Min Act: -0.0000

Data Index: 847846 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8993. Min Act: -0.0000

Data Index: 991932 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8776. Min Act: -0.0000

Data Index: 151021 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1798414 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1151545 (The Pile)

Max Activating Token Index: 563

Text #7

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1701720 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1776133 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1662632 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8320. Min Act: -0.0000

Data Index: 595810 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8142. Min Act: -0.0000

Data Index: 140889 (The Pile)

Max Activating Token Index: 427

Text #12

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1323167 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1372001 (The Pile)

Max Activating Token Index: 107

Text #14

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8099. Min Act: -0.0000

Data Index: 572426 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7919. Min Act: -0.0000

Data Index: 691028 (The Pile)

Max Activating Token Index: 553

Text #16

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1072797 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1626274 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7878. Min Act: -0.0000

Data Index: 720216 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1173056 (The Pile)

Max Activating Token Index: 814