Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3067 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6817. Min Act: -0.0000

Data Index: 549975 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1100894 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1045620 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6132. Min Act: -0.0000

Data Index: 622644 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6199. Min Act: -0.0000

Data Index: 586637 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1214161 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6095. Min Act: -0.0000

Data Index: 264739 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1036258 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1050133 (The Pile)

Max Activating Token Index: 996

Text #9

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1927792 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1096236 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1670545 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5812. Min Act: -0.0001

Data Index: 931359 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5724. Min Act: -0.0000

Data Index: 387422 (The Pile)

Max Activating Token Index: 358

Text #14

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1672150 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5697. Min Act: -0.0000

Data Index: 23572 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5642. Min Act: -0.0000

Data Index: 39838 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1993746 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1695276 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5798. Min Act: -0.0000

Data Index: 98985 (The Pile)

Max Activating Token Index: 120