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

Dataset: The Pile

Neuron 4613 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.3161. Min Act: -0.0000

Data Index: 1351589 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.3892. Min Act: -0.0000

Data Index: 467312 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.1882. Min Act: -0.0000

Data Index: 1481363 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.2070. Min Act: -0.0000

Data Index: 1503590 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.2945. Min Act: -0.0000

Data Index: 1133479 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.4310. Min Act: -0.0000

Data Index: 1975787 (The Pile)

Max Activating Token Index: 250

Text #6

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.2058. Min Act: -0.0000

Data Index: 893809 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.0700. Min Act: -0.0000

Data Index: 959951 (The Pile)

Max Activating Token Index: 892

Text #8

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.1251. Min Act: -0.0000

Data Index: 586502 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.1672. Min Act: -0.0000

Data Index: 1207679 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 7.4310. Min Range: -7.4310

Max Act: 6.9433. Min Act: -0.0000

Data Index: 354395 (The Pile)

Max Activating Token Index: 783

Text #11

Max Range: 7.4310. Min Range: -7.4310

Max Act: 6.9611. Min Act: -0.0000

Data Index: 1307302 (The Pile)

Max Activating Token Index: 784

Text #12

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.1016. Min Act: -0.0000

Data Index: 1089010 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.0820. Min Act: -0.0000

Data Index: 1526830 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 7.4310. Min Range: -7.4310

Max Act: 6.8740. Min Act: -0.0000

Data Index: 1146133 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 7.4310. Min Range: -7.4310

Max Act: 6.6609. Min Act: -0.0000

Data Index: 1281820 (The Pile)

Max Activating Token Index: 684

Text #16

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.2514. Min Act: -0.0000

Data Index: 1005492 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 7.4310. Min Range: -7.4310

Max Act: 6.9725. Min Act: -0.0000

Data Index: 236970 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.0351. Min Act: -0.0000

Data Index: 116845 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 7.4310. Min Range: -7.4310

Max Act: 7.0182. Min Act: -0.0000

Data Index: 1408538 (The Pile)

Max Activating Token Index: 546