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

Dataset: The Pile

Neuron 4268 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: 3.6829. Min Range: -3.6829

Max Act: 3.6829. Min Act: -0.0000

Data Index: 5247 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.6748. Min Act: -0.0000

Data Index: 1858199 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.5260. Min Act: -0.0000

Data Index: 1422576 (The Pile)

Max Activating Token Index: 266

Text #3

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.4812. Min Act: -0.0000

Data Index: 1046320 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.3710. Min Act: -0.0000

Data Index: 487869 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.3129. Min Act: -0.0000

Data Index: 437337 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.3278. Min Act: -0.0000

Data Index: 1506323 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.1744. Min Act: -0.0000

Data Index: 1661266 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.0820. Min Act: -0.0000

Data Index: 1330028 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.2102. Min Act: -0.0000

Data Index: 190607 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.3522. Min Act: -0.0000

Data Index: 1177472 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.1016. Min Act: -0.0000

Data Index: 697543 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.9303. Min Act: -0.0000

Data Index: 1453157 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.0676. Min Act: -0.0000

Data Index: 464719 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.0450. Min Act: -0.0000

Data Index: 976089 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.8065. Min Act: -0.0000

Data Index: 127547 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.7552. Min Act: -0.0000

Data Index: 954128 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.5746. Min Act: -0.0000

Data Index: 434946 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.8472. Min Act: -0.0000

Data Index: 1305038 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.8294. Min Act: -0.0000

Data Index: 1477649 (The Pile)

Max Activating Token Index: 428