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

Dataset: The Pile

Neuron 2919 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.2580. Min Act: -0.0000

Data Index: 1295379 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1452127 (The Pile)

Max Activating Token Index: 809

Text #2

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1993133 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1346062 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1581. Min Act: -0.0000

Data Index: 66305 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1554. Min Act: -0.0000

Data Index: 96159 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1524. Min Act: -0.0000

Data Index: 595203 (The Pile)

Max Activating Token Index: 701

Text #7

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1551. Min Act: -0.0000

Data Index: 327850 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1624. Min Act: -0.0000

Data Index: 475108 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1009930 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1444. Min Act: -0.0000

Data Index: 111834 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1379577 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1998688 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1302. Min Act: -0.0000

Data Index: 898298 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1380. Min Act: -0.0000

Data Index: 563623 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1634585 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1343. Min Act: -0.0000

Data Index: 475564 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1897548 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1143. Min Act: -0.0000

Data Index: 316009 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1346. Min Act: -0.0000

Data Index: 8364 (The Pile)

Max Activating Token Index: 931