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

Dataset: The Pile

Neuron 4252 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8897. Min Act: -0.0000

Data Index: 244688 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8750. Min Act: -0.0000

Data Index: 607116 (The Pile)

Max Activating Token Index: 304

Text #2

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8704. Min Act: -0.0000

Data Index: 734149 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8500. Min Act: -0.0000

Data Index: 715089 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7564. Min Act: -0.0000

Data Index: 310086 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8164. Min Act: -0.0000

Data Index: 233135 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1468198 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8671. Min Act: -0.0000

Data Index: 838084 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8402. Min Act: -0.0000

Data Index: 751398 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1571544 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7800. Min Act: -0.0000

Data Index: 97843 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8556. Min Act: -0.0000

Data Index: 388012 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1726954 (The Pile)

Max Activating Token Index: 274

Text #13

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1224518 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7497. Min Act: -0.0000

Data Index: 183697 (The Pile)

Max Activating Token Index: 429

Text #15

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7675. Min Act: -0.0000

Data Index: 669779 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1645285 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7822. Min Act: -0.0000

Data Index: 575535 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7594. Min Act: -0.0000

Data Index: 325173 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.7366. Min Act: -0.0000

Data Index: 191130 (The Pile)

Max Activating Token Index: 113