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

Dataset: The Pile

Neuron 3052 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1593. Min Act: -0.0000

Data Index: 68746 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1440615 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1292. Min Act: -0.0000

Data Index: 19564 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1680572 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1344. Min Act: -0.0000

Data Index: 165164 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1591732 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1203. Min Act: -0.0000

Data Index: 897588 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1265. Min Act: -0.0000

Data Index: 914449 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1256. Min Act: -0.0000

Data Index: 814924 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1128. Min Act: -0.0000

Data Index: 707322 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1406654 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1067. Min Act: -0.0000

Data Index: 11373 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1239449 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1135914 (The Pile)

Max Activating Token Index: 446

Text #14

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1070. Min Act: -0.0000

Data Index: 898220 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1163. Min Act: -0.0000

Data Index: 646224 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1951681 (The Pile)

Max Activating Token Index: 507

Text #17

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1812822 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0946. Min Act: -0.0000

Data Index: 337861 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1005. Min Act: -0.0000

Data Index: 113677 (The Pile)

Max Activating Token Index: 460