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

Dataset: The Pile

Neuron 672 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: 1.6642. Min Range: -1.6642

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1737247 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.6563. Min Act: -0.0000

Data Index: 810724 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.5466. Min Act: -0.0000

Data Index: 1712767 (The Pile)

Max Activating Token Index: 806

Text #3

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.5568. Min Act: -0.0000

Data Index: 276375 (The Pile)

Max Activating Token Index: 543

Text #4

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.4229. Min Act: -0.0000

Data Index: 758592 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.4258. Min Act: -0.0000

Data Index: 1680197 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.2783. Min Act: -0.0000

Data Index: 333015 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1278042 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1253929 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.2978. Min Act: 0.0000

Data Index: 92630 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.2873. Min Act: -0.0000

Data Index: 584957 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1365725 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.2449. Min Act: -0.0000

Data Index: 416044 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.1768. Min Act: 0.0000

Data Index: 1297792 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.1613. Min Act: 0.0000

Data Index: 1724945 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1673288 (The Pile)

Max Activating Token Index: 785

Text #16

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.2952. Min Act: -0.0000

Data Index: 549107 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.1292. Min Act: -0.0000

Data Index: 342012 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 1.6642. Min Range: -1.6642

Max Act: 1.1285. Min Act: -0.0000

Data Index: 310855 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 1.6642. Min Range: -1.6642

Max Act: 0.9867. Min Act: -0.0000

Data Index: 789664 (The Pile)

Max Activating Token Index: 515