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

Dataset: The Pile

Neuron 3364 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: 5.8530. Min Range: -5.8530

Max Act: 5.8530. Min Act: -0.0000

Data Index: 256701 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.3605. Min Act: -0.0000

Data Index: 1038998 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 5.8530. Min Range: -5.8530

Max Act: 5.5716. Min Act: -0.0000

Data Index: 1041414 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.4667. Min Act: -0.0000

Data Index: 1306149 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.1525. Min Act: -0.0000

Data Index: 1530949 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.8525. Min Act: -0.0000

Data Index: 1047507 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 5.8530. Min Range: -5.8530

Max Act: 4.2373. Min Act: -0.0000

Data Index: 483430 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.1053. Min Act: -0.0000

Data Index: 694202 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.2049. Min Act: -0.0000

Data Index: 1401071 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.5967. Min Act: -0.0000

Data Index: 599639 (The Pile)

Max Activating Token Index: 695

Text #10

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.0902. Min Act: -0.0000

Data Index: 265019 (The Pile)

Max Activating Token Index: 510

Text #11

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.1938. Min Act: -0.0000

Data Index: 1196331 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.2395. Min Act: -0.0000

Data Index: 344838 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 5.8530. Min Range: -5.8530

Max Act: 2.7482. Min Act: -0.0000

Data Index: 1050391 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 5.8530. Min Range: -5.8530

Max Act: 2.9362. Min Act: -0.0000

Data Index: 271390 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.2445. Min Act: -0.0000

Data Index: 1453692 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.2156. Min Act: -0.0000

Data Index: 260103 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.1799. Min Act: -0.0000

Data Index: 592905 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 5.8530. Min Range: -5.8530

Max Act: 2.8546. Min Act: -0.0000

Data Index: 371472 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 5.8530. Min Range: -5.8530

Max Act: 3.2686. Min Act: -0.0000

Data Index: 999247 (The Pile)

Max Activating Token Index: 868