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

Dataset: The Pile

Neuron 1478 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1388007 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2900. Min Act: -0.0000

Data Index: 528770 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1452047 (The Pile)

Max Activating Token Index: 79

Text #3

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1757096 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2243. Min Act: -0.0000

Data Index: 164440 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1995. Min Act: -0.0000

Data Index: 513733 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2096. Min Act: -0.0000

Data Index: 100119 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1319684 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1941. Min Act: -0.0000

Data Index: 938829 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2317. Min Act: -0.0000

Data Index: 580307 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1515713 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1782563 (The Pile)

Max Activating Token Index: 801

Text #12

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2077. Min Act: -0.0000

Data Index: 371684 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1686945 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1736873 (The Pile)

Max Activating Token Index: 502

Text #15

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1518272 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1117268 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1876. Min Act: -0.0000

Data Index: 949949 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1580202 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.1602. Min Act: -0.0000

Data Index: 445195 (The Pile)

Max Activating Token Index: 423