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

Dataset: The Pile

Neuron 1990 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: 2.1016. Min Range: -2.1016

Max Act: 2.1016. Min Act: -0.0000

Data Index: 1190324 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.8019. Min Act: -0.0000

Data Index: 1056294 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.3864. Min Act: -0.0000

Data Index: 1573166 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.4798. Min Act: -0.0000

Data Index: 304343 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1003234 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.3600. Min Act: -0.0000

Data Index: 705633 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2922. Min Act: -0.0000

Data Index: 862176 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1209522 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1646678 (The Pile)

Max Activating Token Index: 576

Text #9

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.3037. Min Act: -0.0000

Data Index: 916299 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1279434 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2609. Min Act: -0.0000

Data Index: 1212733 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1217357 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2720. Min Act: -0.0000

Data Index: 183623 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1470017 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2314. Min Act: -0.0000

Data Index: 801062 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2241. Min Act: -0.0000

Data Index: 201577 (The Pile)

Max Activating Token Index: 729

Text #17

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2483. Min Act: 0.0000

Data Index: 1548398 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1391713 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1140020 (The Pile)

Max Activating Token Index: 548