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

Dataset: The Pile

Neuron 2752 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2308. Min Act: -0.0000

Data Index: 224109 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2207. Min Act: -0.0000

Data Index: 754926 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1664980 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1713146 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1986. Min Act: -0.0000

Data Index: 307051 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1148096 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1570663 (The Pile)

Max Activating Token Index: 90

Text #7

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1916. Min Act: -0.0000

Data Index: 786449 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1944799 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1560491 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1953. Min Act: -0.0000

Data Index: 875889 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1806. Min Act: -0.0000

Data Index: 398952 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1911. Min Act: -0.0000

Data Index: 212328 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1822. Min Act: -0.0000

Data Index: 253075 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1109859 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1367696 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1789. Min Act: -0.0000

Data Index: 163230 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1816. Min Act: -0.0000

Data Index: 123525 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1435536 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1794960 (The Pile)

Max Activating Token Index: 450