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

Dataset: The Pile

Neuron 3980 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1638617 (The Pile)

Max Activating Token Index: 802

Text #1

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1604080 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.7306. Min Act: -0.0000

Data Index: 136777 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6698. Min Act: -0.0000

Data Index: 465281 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6809. Min Act: -0.0000

Data Index: 495294 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1563325 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.7285. Min Act: -0.0000

Data Index: 461639 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1971090 (The Pile)

Max Activating Token Index: 819

Text #8

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6914. Min Act: -0.0000

Data Index: 694400 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1924581 (The Pile)

Max Activating Token Index: 955

Text #10

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6799. Min Act: -0.0000

Data Index: 351021 (The Pile)

Max Activating Token Index: 70

Text #11

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1733647 (The Pile)

Max Activating Token Index: 944

Text #12

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1260135 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1023913 (The Pile)

Max Activating Token Index: 733

Text #14

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1696987 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1701324 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1908726 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1807193 (The Pile)

Max Activating Token Index: 6

Text #18

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1690225 (The Pile)

Max Activating Token Index: 6

Text #19

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1226708 (The Pile)

Max Activating Token Index: 6