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

Dataset: The Pile

Neuron 2075 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: 0.9220. Min Range: -0.9220

Max Act: 0.9220. Min Act: -0.0000

Data Index: 126653 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1643537 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1107668 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1896331 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7672. Min Act: -0.0000

Data Index: 599032 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8010. Min Act: -0.0000

Data Index: 498595 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1721693 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7290. Min Act: -0.0000

Data Index: 832551 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8615. Min Act: -0.0000

Data Index: 435115 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1419474 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1365569 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1063768 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1633229 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1031052 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6437. Min Act: -0.0000

Data Index: 811090 (The Pile)

Max Activating Token Index: 903

Text #15

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6871. Min Act: -0.0000

Data Index: 619779 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1264836 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7036. Min Act: -0.0000

Data Index: 141117 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1572305 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1772524 (The Pile)

Max Activating Token Index: 67