Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1551291 (The Pile)

Max Activating Token Index: 951

Text #1

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1607540 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4979. Min Act: -0.0000

Data Index: 191108 (The Pile)

Max Activating Token Index: 916

Text #3

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4947. Min Act: -0.0000

Data Index: 591389 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1704039 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5272. Min Act: -0.0000

Data Index: 97603 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1695809 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4558. Min Act: -0.0000

Data Index: 498016 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1861040 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5072. Min Act: -0.0000

Data Index: 269317 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5112. Min Act: 0.0000

Data Index: 1059928 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4383. Min Act: -0.0000

Data Index: 205375 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4676. Min Act: 0.0000

Data Index: 1286261 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4335. Min Act: -0.0000

Data Index: 932962 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4324. Min Act: -0.0000

Data Index: 90165 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1662707 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4355. Min Act: 0.0000

Data Index: 1504075 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4527. Min Act: 0.0000

Data Index: 330792 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1565418 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4158. Min Act: 0.0000

Data Index: 1486379 (The Pile)

Max Activating Token Index: 986