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

Dataset: The Pile

Neuron 3012 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: 0.8814. Min Range: -0.8814

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1487517 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7547. Min Act: -0.0000

Data Index: 760231 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1966241 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1562650 (The Pile)

Max Activating Token Index: 605

Text #4

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1170476 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1345918 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6928. Min Act: -0.0000

Data Index: 738201 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6915. Min Act: -0.0000

Data Index: 110331 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6937. Min Act: -0.0000

Data Index: 355536 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1849629 (The Pile)

Max Activating Token Index: 705

Text #10

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.5917. Min Act: -0.0000

Data Index: 522705 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1026972 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.5968. Min Act: -0.0000

Data Index: 589147 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1922448 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.5768. Min Act: -0.0000

Data Index: 248970 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.5452. Min Act: -0.0000

Data Index: 830400 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.5331. Min Act: -0.0000

Data Index: 703380 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1405205 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6057. Min Act: -0.0000

Data Index: 731631 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1913192 (The Pile)

Max Activating Token Index: 645