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

Dataset: The Pile

Neuron 3820 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1491091 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1066433 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1324794 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1923332 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0383. Min Act: -0.0000

Data Index: 1761985 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1199072 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1249909 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0296. Min Act: -0.0000

Data Index: 1575602 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0129. Min Act: -0.0000

Data Index: 42298 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0328. Min Act: -0.0000

Data Index: 9468 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9645. Min Act: -0.0000

Data Index: 420435 (The Pile)

Max Activating Token Index: 979

Text #11

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0442. Min Act: -0.0000

Data Index: 524025 (The Pile)

Max Activating Token Index: 972

Text #12

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0172. Min Act: -0.0000

Data Index: 1948573 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1208697 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1671656 (The Pile)

Max Activating Token Index: 711

Text #15

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1247443 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1664067 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1358747 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9658. Min Act: -0.0000

Data Index: 841878 (The Pile)

Max Activating Token Index: 627

Text #19

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1569469 (The Pile)

Max Activating Token Index: 641