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

Dataset: The Pile

Neuron 954 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: 0.4589. Min Range: -0.4589

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1516568 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3844. Min Act: -0.0000

Data Index: 831090 (The Pile)

Max Activating Token Index: 474

Text #2

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1369200 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1385874 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1132455 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1607699 (The Pile)

Max Activating Token Index: 761

Text #6

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3979. Min Act: -0.0000

Data Index: 644440 (The Pile)

Max Activating Token Index: 725

Text #7

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1650116 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3579. Min Act: -0.0000

Data Index: 513180 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1183386 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3641. Min Act: -0.0000

Data Index: 371285 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1217085 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3511. Min Act: -0.0000

Data Index: 125466 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1209289 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1613165 (The Pile)

Max Activating Token Index: 839

Text #15

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1698534 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1608544 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1352190 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3246. Min Act: -0.0000

Data Index: 212411 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3332. Min Act: -0.0000

Data Index: 542205 (The Pile)

Max Activating Token Index: 82