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

Dataset: The Pile

Neuron 1818 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.8363. Min Act: -0.0000

Data Index: 590340 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6725. Min Act: 0.0000

Data Index: 863029 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6883. Min Act: -0.0000

Data Index: 835090 (The Pile)

Max Activating Token Index: 546

Text #3

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5993. Min Act: 0.0000

Data Index: 508244 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1965398 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6283. Min Act: -0.0000

Data Index: 294950 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1222105 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1063665 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1269690 (The Pile)

Max Activating Token Index: 918

Text #9

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5742. Min Act: -0.0000

Data Index: 747390 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5344. Min Act: 0.0000

Data Index: 1698656 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1825158 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5037. Min Act: -0.0000

Data Index: 997718 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1838410 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4162. Min Act: -0.0000

Data Index: 975791 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4483. Min Act: -0.0000

Data Index: 337274 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1190160 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4192. Min Act: -0.0000

Data Index: 509873 (The Pile)

Max Activating Token Index: 854

Text #18

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4220. Min Act: 0.0000

Data Index: 571181 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4368. Min Act: -0.0000

Data Index: 435862 (The Pile)

Max Activating Token Index: 871