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

Dataset: The Pile

Neuron 1009 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.5502. Min Act: -0.0000

Data Index: 142869 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.0517. Min Act: -0.0000

Data Index: 14986 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.9997. Min Act: -0.0000

Data Index: 901946 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.9300. Min Act: -0.0000

Data Index: 622704 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1123331 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8157. Min Act: -0.0000

Data Index: 524886 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.6364. Min Act: -0.0000

Data Index: 718189 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7587. Min Act: -0.0000

Data Index: 570980 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1515463 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1633326 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7464. Min Act: -0.0000

Data Index: 672695 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1871791 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1961894 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7252. Min Act: -0.0000

Data Index: 743343 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1480712 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1872513 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.6818. Min Act: -0.0000

Data Index: 358244 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1447147 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.5196. Min Act: -0.0000

Data Index: 321275 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.6971. Min Act: -0.0000

Data Index: 491774 (The Pile)

Max Activating Token Index: 959