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

Dataset: The Pile

Neuron 2278 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1852. Min Range: -8.1852

Max Act: 8.1852. Min Act: -0.0000

Data Index: 965503 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 8.1852. Min Range: -8.1852

Max Act: 7.7632. Min Act: -0.0000

Data Index: 1859263 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 8.1852. Min Range: -8.1852

Max Act: 6.2952. Min Act: -0.0000

Data Index: 719761 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 8.1852. Min Range: -8.1852

Max Act: 6.3054. Min Act: -0.0000

Data Index: 1456332 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 8.1852. Min Range: -8.1852

Max Act: 5.6892. Min Act: -0.0000

Data Index: 375005 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 8.1852. Min Range: -8.1852

Max Act: 6.1826. Min Act: -0.0000

Data Index: 1584941 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 8.1852. Min Range: -8.1852

Max Act: 5.8364. Min Act: -0.0000

Data Index: 1572564 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 8.1852. Min Range: -8.1852

Max Act: 5.3085. Min Act: -0.0000

Data Index: 1610891 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 8.1852. Min Range: -8.1852

Max Act: 4.6666. Min Act: -0.0000

Data Index: 1247588 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 8.1852. Min Range: -8.1852

Max Act: 4.9889. Min Act: -0.0000

Data Index: 1284006 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 8.1852. Min Range: -8.1852

Max Act: 4.7724. Min Act: -0.0000

Data Index: 1675902 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 8.1852. Min Range: -8.1852

Max Act: 4.8745. Min Act: -0.0000

Data Index: 644927 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 8.1852. Min Range: -8.1852

Max Act: 5.0861. Min Act: -0.0000

Data Index: 1169880 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 8.1852. Min Range: -8.1852

Max Act: 5.2090. Min Act: -0.0000

Data Index: 335821 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 8.1852. Min Range: -8.1852

Max Act: 4.6788. Min Act: -0.0000

Data Index: 123656 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 8.1852. Min Range: -8.1852

Max Act: 4.4637. Min Act: -0.0000

Data Index: 598519 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 8.1852. Min Range: -8.1852

Max Act: 5.1784. Min Act: -0.0000

Data Index: 1690903 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 8.1852. Min Range: -8.1852

Max Act: 4.8043. Min Act: -0.0000

Data Index: 1227663 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 8.1852. Min Range: -8.1852

Max Act: 4.6575. Min Act: -0.0000

Data Index: 261232 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 8.1852. Min Range: -8.1852

Max Act: 4.7685. Min Act: -0.0000

Data Index: 1155447 (The Pile)

Max Activating Token Index: 437