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

Dataset: The Pile

Neuron 204 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9922. Min Act: -0.0000

Data Index: 39701 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 1.0064. Min Range: -1.0064

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1683805 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1856384 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9019. Min Act: -0.0000

Data Index: 1495182 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9803. Min Act: -0.0000

Data Index: 460725 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1511750 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1607267 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1289203 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.9279. Min Act: -0.0000

Data Index: 596447 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1241167 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8608. Min Act: -0.0000

Data Index: 544670 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1422200 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1912513 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8494. Min Act: -0.0000

Data Index: 42111 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8954. Min Act: -0.0000

Data Index: 275931 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8658. Min Act: -0.0000

Data Index: 55340 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7209. Min Act: -0.0000

Data Index: 100995 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1677140 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.7775. Min Act: -0.0000

Data Index: 132059 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 1.0064. Min Range: -1.0064

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1305400 (The Pile)

Max Activating Token Index: 1019