Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5055 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4720. Min Act: -0.0000

Data Index: 1166482 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4523. Min Act: -0.0000

Data Index: 648310 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4044. Min Act: -0.0000

Data Index: 756635 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.2970. Min Act: -0.0000

Data Index: 445248 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.2436. Min Act: -0.0000

Data Index: 947642 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1699230 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1086553 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.1462. Min Act: -0.0000

Data Index: 472905 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.2733. Min Act: -0.0000

Data Index: 426357 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.1725. Min Act: -0.0000

Data Index: 1355411 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.2319. Min Act: -0.0000

Data Index: 810775 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.0297. Min Act: -0.0000

Data Index: 224705 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1190449 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.4720. Min Range: -1.4720

Max Act: 0.9900. Min Act: -0.0000

Data Index: 493430 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.2438. Min Act: -0.0000

Data Index: 74706 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1855410 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1259433 (The Pile)

Max Activating Token Index: 398

Text #17

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1662779 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 1.4720. Min Range: -1.4720

Max Act: 0.9959. Min Act: -0.0000

Data Index: 293278 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.0636. Min Act: -0.0000

Data Index: 450316 (The Pile)

Max Activating Token Index: 301