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

Dataset: The Pile

Neuron 2499 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1882. Min Act: -0.0000

Data Index: 568259 (The Pile)

Max Activating Token Index: 401

Text #1

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1764. Min Act: -0.0000

Data Index: 690391 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1871661 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1797241 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1562. Min Act: -0.0000

Data Index: 951262 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1832526 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1544. Min Act: -0.0000

Data Index: 933041 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1598. Min Act: -0.0000

Data Index: 36199 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1525. Min Act: -0.0000

Data Index: 898950 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1331624 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1765337 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1350. Min Act: -0.0000

Data Index: 250005 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1391. Min Act: -0.0000

Data Index: 272920 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1441. Min Act: -0.0000

Data Index: 462638 (The Pile)

Max Activating Token Index: 499

Text #14

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1984665 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1938121 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1287. Min Act: -0.0000

Data Index: 274657 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1441197 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1872024 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1281. Min Act: -0.0000

Data Index: 587487 (The Pile)

Max Activating Token Index: 304