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

Dataset: The Pile

Neuron 760 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: 0.6970. Min Range: -0.6970

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1105139 (The Pile)

Max Activating Token Index: 810

Text #1

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1140998 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1923849 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.6086. Min Act: -0.0000

Data Index: 301706 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5936. Min Act: -0.0000

Data Index: 605226 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5735. Min Act: -0.0000

Data Index: 433913 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1559909 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1947737 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1211721 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1826331 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1532251 (The Pile)

Max Activating Token Index: 28

Text #11

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1053394 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1129123 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1754476 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1676867 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1001415 (The Pile)

Max Activating Token Index: 928

Text #16

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1773073 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1794266 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1690979 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 0.6970. Min Range: -0.6970

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1144561 (The Pile)

Max Activating Token Index: 73