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

Dataset: The Pile

Neuron 147 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.2370. Min Act: -0.0000

Data Index: 107824 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1358987 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1865918 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1526674 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.0967. Min Act: -0.0000

Data Index: 666405 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.0022. Min Act: -0.0000

Data Index: 1883851 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9482. Min Act: -0.0000

Data Index: 324192 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1741921 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1320948 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1221982 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9970. Min Act: -0.0000

Data Index: 937220 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.0253. Min Act: -0.0000

Data Index: 206921 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1484853 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9035. Min Act: -0.0000

Data Index: 255298 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9154. Min Act: -0.0000

Data Index: 430699 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1928637 (The Pile)

Max Activating Token Index: 302

Text #16

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1559490 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.8580. Min Act: -0.0000

Data Index: 362703 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9702. Min Act: -0.0000

Data Index: 657957 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1336917 (The Pile)

Max Activating Token Index: 38