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

Dataset: The Pile

Neuron 3092 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: 0.4637. Min Range: -0.4637

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1505451 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1266701 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1360716 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3053. Min Act: -0.0000

Data Index: 917208 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1906927 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1587119 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1116371 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1638508 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1557420 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1867620 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2518. Min Act: -0.0000

Data Index: 137882 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1624224 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1767834 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2770. Min Act: -0.0000

Data Index: 566979 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1594657 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2536. Min Act: -0.0000

Data Index: 132402 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2712. Min Act: -0.0000

Data Index: 919758 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2631. Min Act: -0.0000

Data Index: 681112 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2688. Min Act: -0.0000

Data Index: 365701 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1839844 (The Pile)

Max Activating Token Index: 412