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

Dataset: The Pile

Neuron 1781 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.8033. Min Act: 0.0000

Data Index: 1711828 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.7962. Min Act: 0.0000

Data Index: 1525012 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6996. Min Act: -0.0001

Data Index: 1090577 (The Pile)

Max Activating Token Index: 688

Text #3

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1302357 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1336268 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.7301. Min Act: -0.0000

Data Index: 51107 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6912. Min Act: -0.0000

Data Index: 412714 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6785. Min Act: -0.0000

Data Index: 43422 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6581. Min Act: 0.0000

Data Index: 160104 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1422745 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1905585 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6233. Min Act: -0.0000

Data Index: 734144 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6413. Min Act: -0.0000

Data Index: 974782 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6454. Min Act: 0.0000

Data Index: 206743 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6045. Min Act: -0.0000

Data Index: 400 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6167. Min Act: 0.0000

Data Index: 1061983 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.7334. Min Act: 0.0000

Data Index: 169541 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6667. Min Act: -0.0000

Data Index: 961182 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1222383 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6132. Min Act: -0.0000

Data Index: 268383 (The Pile)

Max Activating Token Index: 208