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

Dataset: The Pile

Neuron 3302 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: 1.3854. Min Range: -1.3854

Max Act: 1.3854. Min Act: -0.0000

Data Index: 1339128 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1463744 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.2384. Min Act: -0.0000

Data Index: 962457 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1590547 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1391696 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.2478. Min Act: -0.0000

Data Index: 1230828 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1034100 (The Pile)

Max Activating Token Index: 952

Text #7

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1662356 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1551. Min Act: -0.0000

Data Index: 833842 (The Pile)

Max Activating Token Index: 576

Text #9

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1166740 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1081248 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1148. Min Act: -0.0000

Data Index: 401445 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1652664 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1441. Min Act: -0.0000

Data Index: 546834 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1826. Min Act: -0.0000

Data Index: 1389833 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1391. Min Act: -0.0000

Data Index: 199256 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1014. Min Act: -0.0000

Data Index: 663315 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1302. Min Act: -0.0000

Data Index: 374654 (The Pile)

Max Activating Token Index: 624

Text #18

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1537. Min Act: -0.0000

Data Index: 1702132 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1732704 (The Pile)

Max Activating Token Index: 784