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

Dataset: The Pile

Neuron 4553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0000

Data Index: 955194 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1875882 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1954248 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1500614 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1613. Min Act: -0.0000

Data Index: 120705 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1300097 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1558. Min Act: -0.0000

Data Index: 943697 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1431. Min Act: -0.0000

Data Index: 33697 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1570579 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1383. Min Act: -0.0000

Data Index: 852971 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1798328 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1351. Min Act: -0.0000

Data Index: 363537 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1408. Min Act: -0.0000

Data Index: 328140 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1193945 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1310. Min Act: -0.0000

Data Index: 40295 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1517103 (The Pile)

Max Activating Token Index: 782

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1473. Min Act: -0.0000

Data Index: 362565 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1056902 (The Pile)

Max Activating Token Index: 910

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1200. Min Act: -0.0000

Data Index: 859959 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1280102 (The Pile)

Max Activating Token Index: 990