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

Dataset: The Pile

Neuron 3609 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.7105. Min Act: -0.0000

Data Index: 1642849 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.7274. Min Act: -0.0001

Data Index: 666573 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.6409. Min Act: -0.0000

Data Index: 1746771 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.5753. Min Act: -0.0001

Data Index: 1923824 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.7519. Min Act: -0.0001

Data Index: 207457 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.5889. Min Act: -0.0000

Data Index: 692808 (The Pile)

Max Activating Token Index: 617

Text #6

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.4962. Min Act: -0.0001

Data Index: 1599430 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.5504. Min Act: -0.0000

Data Index: 1321852 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.5353. Min Act: -0.0000

Data Index: 1247552 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1991407 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.4120. Min Act: -0.0001

Data Index: 1664645 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.4654. Min Act: -0.0000

Data Index: 535380 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.2696. Min Act: -0.0000

Data Index: 900293 (The Pile)

Max Activating Token Index: 561

Text #13

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.4328. Min Act: -0.0000

Data Index: 1043905 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.3667. Min Act: -0.0001

Data Index: 142268 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.4350. Min Act: -0.0001

Data Index: 1072936 (The Pile)

Max Activating Token Index: 866

Text #16

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.3304. Min Act: -0.0001

Data Index: 1227834 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1014836 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1707125 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.3599. Min Act: -0.0000

Data Index: 738157 (The Pile)

Max Activating Token Index: 206