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

Dataset: The Pile

Neuron 1538 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: 1.1646. Min Range: -1.1646

Max Act: 1.1185. Min Act: -0.0000

Data Index: 1639090 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 1.1646. Min Range: -1.1646

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1043938 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9974. Min Act: -0.0000

Data Index: 698303 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 1.1646. Min Range: -1.1646

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1096698 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1954902 (The Pile)

Max Activating Token Index: 579

Text #5

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8766. Min Act: -0.0000

Data Index: 1347455 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1836101 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8953. Min Act: -0.0000

Data Index: 1683419 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8589. Min Act: -0.0000

Data Index: 67664 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.7406. Min Act: -0.0000

Data Index: 771261 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1498668 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8128. Min Act: -0.0000

Data Index: 450436 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1996154 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.7587. Min Act: -0.0000

Data Index: 922356 (The Pile)

Max Activating Token Index: 706

Text #14

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8142. Min Act: -0.0000

Data Index: 271533 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.8155. Min Act: -0.0000

Data Index: 305891 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.7809. Min Act: -0.0000

Data Index: 333773 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1906800 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1902285 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 1.1646. Min Range: -1.1646

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1058863 (The Pile)

Max Activating Token Index: 113