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

Dataset: The Pile

Neuron 1412 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: 1.1147. Min Range: -1.1147

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1697026 (The Pile)

Max Activating Token Index: 749

Text #1

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1907901 (The Pile)

Max Activating Token Index: 216

Text #2

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1157452 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1899610 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.8491. Min Act: -0.0000

Data Index: 520997 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7805. Min Act: -0.0000

Data Index: 892342 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1516413 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7545. Min Act: -0.0000

Data Index: 377116 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7818. Min Act: -0.0000

Data Index: 516174 (The Pile)

Max Activating Token Index: 362

Text #9

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1093308 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7679. Min Act: -0.0000

Data Index: 104437 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7428. Min Act: -0.0000

Data Index: 79549 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1342463 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1859024 (The Pile)

Max Activating Token Index: 322

Text #14

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1474461 (The Pile)

Max Activating Token Index: 865

Text #15

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1950090 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.7309. Min Act: -0.0000

Data Index: 606117 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.6989. Min Act: -0.0000

Data Index: 729403 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.6968. Min Act: -0.0000

Data Index: 58621 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1626947 (The Pile)

Max Activating Token Index: 540