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

Dataset: The Pile

Neuron 968 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1825604 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1556931 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5620. Min Act: -0.0000

Data Index: 991229 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.6189. Min Act: -0.0000

Data Index: 846313 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1425791 (The Pile)

Max Activating Token Index: 599

Text #5

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1660048 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.6263. Min Act: -0.0000

Data Index: 126526 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1407021 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1425648 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1323973 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1344833 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1154898 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1670883 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1671185 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1445710 (The Pile)

Max Activating Token Index: 648

Text #15

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5461. Min Act: -0.0000

Data Index: 680227 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5421. Min Act: -0.0000

Data Index: 873778 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5133. Min Act: -0.0000

Data Index: 823954 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5167. Min Act: -0.0000

Data Index: 775098 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5176. Min Act: -0.0000

Data Index: 824756 (The Pile)

Max Activating Token Index: 146