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

Dataset: The Pile

Neuron 4 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0839. Min Range: -1.0839

Max Act: 1.0839. Min Act: -0.0000

Data Index: 177034 (The Pile)

Max Activating Token Index: 401

Text #1

Max Range: 1.0839. Min Range: -1.0839

Max Act: 1.0588. Min Act: -0.0000

Data Index: 614817 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1596784 (The Pile)

Max Activating Token Index: 692

Text #3

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1173337 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1815569 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 1.0839. Min Range: -1.0839

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1263310 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1515140 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9801. Min Act: -0.0000

Data Index: 101517 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8916. Min Act: -0.0000

Data Index: 612891 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9564. Min Act: -0.0000

Data Index: 60313 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8654. Min Act: -0.0000

Data Index: 773702 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9271. Min Act: -0.0000

Data Index: 497168 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1707020 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9115. Min Act: -0.0000

Data Index: 728267 (The Pile)

Max Activating Token Index: 1003

Text #14

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9018. Min Act: -0.0000

Data Index: 674881 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9087. Min Act: -0.0000

Data Index: 846429 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9566. Min Act: -0.0000

Data Index: 164137 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1782270 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1898952 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8607. Min Act: -0.0000

Data Index: 536280 (The Pile)

Max Activating Token Index: 292