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

Dataset: The Pile

Neuron 1881 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2545. Min Range: -3.2545

Max Act: 3.2545. Min Act: -0.0000

Data Index: 1711814 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 3.2545. Min Range: -3.2545

Max Act: 2.6269. Min Act: -0.0000

Data Index: 1899941 (The Pile)

Max Activating Token Index: 601

Text #2

Max Range: 3.2545. Min Range: -3.2545

Max Act: 2.2125. Min Act: -0.0000

Data Index: 1587626 (The Pile)

Max Activating Token Index: 830

Text #3

Max Range: 3.2545. Min Range: -3.2545

Max Act: 2.4239. Min Act: -0.0000

Data Index: 1900483 (The Pile)

Max Activating Token Index: 599

Text #4

Max Range: 3.2545. Min Range: -3.2545

Max Act: 2.1492. Min Act: -0.0000

Data Index: 1920508 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 3.2545. Min Range: -3.2545

Max Act: 2.0791. Min Act: -0.0000

Data Index: 1490443 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.8288. Min Act: -0.0000

Data Index: 1764834 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 3.2545. Min Range: -3.2545

Max Act: 2.0692. Min Act: -0.0000

Data Index: 1410393 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 3.2545. Min Range: -3.2545

Max Act: 2.0226. Min Act: -0.0000

Data Index: 1539617 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.8153. Min Act: -0.0000

Data Index: 1021369 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.8482. Min Act: -0.0000

Data Index: 276400 (The Pile)

Max Activating Token Index: 883

Text #11

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.7694. Min Act: -0.0000

Data Index: 539906 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 3.2545. Min Range: -3.2545

Max Act: 2.0682. Min Act: -0.0000

Data Index: 744198 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.6580. Min Act: -0.0000

Data Index: 600556 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.8015. Min Act: -0.0000

Data Index: 1804066 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.9993. Min Act: -0.0000

Data Index: 849420 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.8847. Min Act: -0.0000

Data Index: 924651 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.7946. Min Act: -0.0000

Data Index: 696451 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.8656. Min Act: -0.0000

Data Index: 713844 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 3.2545. Min Range: -3.2545

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1041606 (The Pile)

Max Activating Token Index: 69