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

Dataset: The Pile

Neuron 280 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.2857. Min Act: -0.0000

Data Index: 360183 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.7607. Min Act: -0.0000

Data Index: 199381 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.1682. Min Act: -0.0000

Data Index: 1849284 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.2042. Min Act: -0.0000

Data Index: 1722636 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.3457. Min Act: -0.0000

Data Index: 803791 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.1932. Min Act: -0.0000

Data Index: 1213941 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.2196. Min Act: -0.0000

Data Index: 1432187 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.2018. Min Act: -0.0000

Data Index: 652309 (The Pile)

Max Activating Token Index: 451

Text #8

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.3256. Min Act: -0.0000

Data Index: 954177 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.1920. Min Act: -0.0000

Data Index: 199805 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.1818. Min Act: -0.0000

Data Index: 1738177 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.0616. Min Act: -0.0000

Data Index: 1470093 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.1077. Min Act: -0.0000

Data Index: 799341 (The Pile)

Max Activating Token Index: 954

Text #13

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.3476. Min Act: -0.0000

Data Index: 1820270 (The Pile)

Max Activating Token Index: 184

Text #14

Max Range: 3.7607. Min Range: -3.7607

Max Act: 2.8869. Min Act: -0.0000

Data Index: 1528938 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 3.7607. Min Range: -3.7607

Max Act: 2.9755. Min Act: -0.0000

Data Index: 1177264 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 3.7607. Min Range: -3.7607

Max Act: 2.7119. Min Act: -0.0000

Data Index: 1013368 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 3.7607. Min Range: -3.7607

Max Act: 3.0205. Min Act: -0.0000

Data Index: 1861854 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 3.7607. Min Range: -3.7607

Max Act: 2.7112. Min Act: -0.0000

Data Index: 623434 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 3.7607. Min Range: -3.7607

Max Act: 2.6762. Min Act: -0.0000

Data Index: 609038 (The Pile)

Max Activating Token Index: 895