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

Dataset: The Pile

Neuron 3703 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.3324. Min Act: 0.0000

Data Index: 1281405 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.3139. Min Act: -0.0000

Data Index: 174206 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.2891. Min Act: 0.0000

Data Index: 688732 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.2853. Min Act: -0.0000

Data Index: 1662042 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.2507. Min Act: 0.0001

Data Index: 1961341 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.2119. Min Act: -0.0000

Data Index: 985587 (The Pile)

Max Activating Token Index: 260

Text #6

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.1108. Min Act: 0.0000

Data Index: 1403089 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.1032. Min Act: -0.0000

Data Index: 367380 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1240773 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0257. Min Act: -0.0000

Data Index: 597637 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1474363 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1747713 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0493. Min Act: 0.0000

Data Index: 693020 (The Pile)

Max Activating Token Index: 519

Text #13

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9351. Min Act: -0.0000

Data Index: 1213012 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9846. Min Act: 0.0000

Data Index: 1022984 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9818. Min Act: -0.0000

Data Index: 87263 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1264939 (The Pile)

Max Activating Token Index: 405

Text #17

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9659. Min Act: 0.0001

Data Index: 1081361 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1029860 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9302. Min Act: 0.0000

Data Index: 475178 (The Pile)

Max Activating Token Index: 76