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

Dataset: The Pile

Neuron 3321 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: 1.5720. Min Range: -1.5720

Max Act: 1.2478. Min Act: -0.0000

Data Index: 199903 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.5720. Min Act: -0.0000

Data Index: 1361412 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1226124 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.3986. Min Act: -0.0000

Data Index: 719388 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1464621 (The Pile)

Max Activating Token Index: 867

Text #5

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2706. Min Act: -0.0000

Data Index: 503525 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.3160. Min Act: -0.0000

Data Index: 1411770 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2828. Min Act: -0.0000

Data Index: 1724078 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2913. Min Act: -0.0000

Data Index: 1177552 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2226. Min Act: -0.0000

Data Index: 215198 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2721. Min Act: -0.0000

Data Index: 670946 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2987. Min Act: -0.0000

Data Index: 46424 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2614. Min Act: -0.0000

Data Index: 638647 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.3393. Min Act: -0.0000

Data Index: 657144 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1287619 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1544535 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1144880 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1956456 (The Pile)

Max Activating Token Index: 925

Text #18

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.1374. Min Act: -0.0000

Data Index: 246111 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 1.5720. Min Range: -1.5720

Max Act: 1.2658. Min Act: -0.0000

Data Index: 919853 (The Pile)

Max Activating Token Index: 635