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

Dataset: The Pile

Neuron 2363 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: 1.5796. Min Range: -1.5796

Max Act: 1.5796. Min Act: -0.0000

Data Index: 1551198 (The Pile)

Max Activating Token Index: 778

Text #1

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3849. Min Act: -0.0000

Data Index: 876395 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1220511 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3257. Min Act: -0.0000

Data Index: 484876 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3418. Min Act: -0.0000

Data Index: 751374 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1794. Min Act: -0.0000

Data Index: 45892 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1407. Min Act: -0.0000

Data Index: 731901 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1875145 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1538402 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.2026. Min Act: -0.0000

Data Index: 1974966 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1805214 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1848. Min Act: -0.0000

Data Index: 894585 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.0982. Min Act: -0.0000

Data Index: 349235 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1139. Min Act: -0.0000

Data Index: 267668 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.0656. Min Act: -0.0000

Data Index: 914669 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1940. Min Act: -0.0000

Data Index: 1595349 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1181. Min Act: -0.0000

Data Index: 8836 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1102322 (The Pile)

Max Activating Token Index: 893

Text #18

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1888572 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1377176 (The Pile)

Max Activating Token Index: 648