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

Dataset: The Pile

Neuron 3199 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: 0.5671. Min Range: -0.5671

Max Act: 0.5671. Min Act: -0.0000

Data Index: 183053 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1654079 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1468730 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5129. Min Act: -0.0000

Data Index: 461060 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1309761 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4651. Min Act: -0.0000

Data Index: 797358 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5103. Min Act: -0.0000

Data Index: 247267 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1694147 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1022990 (The Pile)

Max Activating Token Index: 25

Text #9

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1775285 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5022. Min Act: -0.0000

Data Index: 636616 (The Pile)

Max Activating Token Index: 15

Text #11

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1545634 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1581400 (The Pile)

Max Activating Token Index: 818

Text #13

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1919408 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1666127 (The Pile)

Max Activating Token Index: 856

Text #15

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4684. Min Act: -0.0000

Data Index: 567678 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1237051 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1793799 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1027432 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1161692 (The Pile)

Max Activating Token Index: 744