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

Dataset: The Pile

Neuron 4683 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1947452 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1628. Min Act: -0.0000

Data Index: 53032 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1026716 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1590. Min Act: -0.0000

Data Index: 50970 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1541. Min Act: -0.0000

Data Index: 243026 (The Pile)

Max Activating Token Index: 579

Text #5

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1265720 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1248200 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1803836 (The Pile)

Max Activating Token Index: 389

Text #8

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1359. Min Act: -0.0000

Data Index: 516999 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1751910 (The Pile)

Max Activating Token Index: 735

Text #10

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1491. Min Act: -0.0000

Data Index: 561487 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1542. Min Act: -0.0000

Data Index: 679357 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1465447 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1420. Min Act: -0.0000

Data Index: 251670 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1416. Min Act: -0.0000

Data Index: 122616 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1322. Min Act: -0.0000

Data Index: 713433 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1817640 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1224917 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1949064 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1366. Min Act: -0.0000

Data Index: 721045 (The Pile)

Max Activating Token Index: 600