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

Dataset: The Pile

Neuron 1504 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1173581 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.9772. Min Act: -0.0000

Data Index: 279067 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1583351 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.9401. Min Act: -0.0000

Data Index: 232713 (The Pile)

Max Activating Token Index: 509

Text #4

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8926. Min Act: -0.0000

Data Index: 250091 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8919. Min Act: -0.0000

Data Index: 25097 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8908. Min Act: -0.0000

Data Index: 723396 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8709. Min Act: -0.0000

Data Index: 844198 (The Pile)

Max Activating Token Index: 4

Text #8

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8941. Min Act: -0.0000

Data Index: 331005 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8537. Min Act: -0.0000

Data Index: 646306 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8548. Min Act: -0.0000

Data Index: 811388 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1353807 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1524101 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1841484 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1491414 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1000195 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1429931 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8488. Min Act: -0.0000

Data Index: 47841 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1169993 (The Pile)

Max Activating Token Index: 646

Text #19

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1778890 (The Pile)

Max Activating Token Index: 313