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

Dataset: The Pile

Neuron 4448 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: 0.2361. Min Range: -0.2361

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1202164 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2361. Min Act: -0.0000

Data Index: 200427 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1793. Min Act: -0.0000

Data Index: 704095 (The Pile)

Max Activating Token Index: 521

Text #3

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1243540 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1836524 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1836. Min Act: -0.0000

Data Index: 723157 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1934. Min Act: -0.0000

Data Index: 1968963 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1911. Min Act: -0.0000

Data Index: 866754 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1862. Min Act: -0.0000

Data Index: 88858 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1884955 (The Pile)

Max Activating Token Index: 208

Text #10

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1794440 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1798. Min Act: -0.0000

Data Index: 982169 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1714. Min Act: -0.0000

Data Index: 737716 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1688. Min Act: -0.0000

Data Index: 157260 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1498410 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1278129 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1499206 (The Pile)

Max Activating Token Index: 811

Text #17

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1649. Min Act: -0.0000

Data Index: 592743 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1682. Min Act: -0.0000

Data Index: 1260281 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1634. Min Act: -0.0000

Data Index: 272763 (The Pile)

Max Activating Token Index: 1015