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

Dataset: The Pile

Neuron 4478 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2251. Min Act: -0.0000

Data Index: 999496 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2470. Min Act: -0.0000

Data Index: 996248 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2028. Min Act: -0.0000

Data Index: 576278 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1182231 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2053. Min Act: -0.0000

Data Index: 170407 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1260663 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1786. Min Act: -0.0000

Data Index: 747917 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1288620 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1731. Min Act: -0.0000

Data Index: 89910 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1955. Min Act: -0.0000

Data Index: 987026 (The Pile)

Max Activating Token Index: 857

Text #10

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1428. Min Act: -0.0000

Data Index: 758230 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1546. Min Act: -0.0000

Data Index: 452998 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1364809 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1588402 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1491. Min Act: -0.0000

Data Index: 51921 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1478. Min Act: -0.0000

Data Index: 192748 (The Pile)

Max Activating Token Index: 703

Text #16

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1571. Min Act: -0.0000

Data Index: 567512 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1526. Min Act: -0.0000

Data Index: 608466 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1385. Min Act: -0.0000

Data Index: 991908 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1160368 (The Pile)

Max Activating Token Index: 69