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

Dataset: The Pile

Neuron 4163 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1873. Min Act: 0.0000

Data Index: 1258559 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1510206 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1559. Min Act: -0.0000

Data Index: 541677 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1093741 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1538. Min Act: -0.0000

Data Index: 95240 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1535. Min Act: -0.0000

Data Index: 313382 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1931487 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1099876 (The Pile)

Max Activating Token Index: 53

Text #8

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1600644 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1618270 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1133694 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1406527 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1396538 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1111520 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1414. Min Act: 0.0000

Data Index: 1223069 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1411. Min Act: -0.0000

Data Index: 288789 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1393. Min Act: -0.0000

Data Index: 302589 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1024581 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1387. Min Act: -0.0000

Data Index: 563810 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1249237 (The Pile)

Max Activating Token Index: 165