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

Dataset: The Pile

Neuron 1652 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: 0.1660. Min Range: -0.1660

Max Act: 0.1660. Min Act: 0.0000

Data Index: 287504 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1654. Min Act: 0.0000

Data Index: 1618880 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1634. Min Act: 0.0000

Data Index: 1982703 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1516. Min Act: 0.0000

Data Index: 781034 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1517. Min Act: 0.0000

Data Index: 670244 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1535. Min Act: 0.0000

Data Index: 1806677 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1602415 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1510. Min Act: 0.0000

Data Index: 1932744 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1455. Min Act: 0.0000

Data Index: 480700 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1450. Min Act: 0.0000

Data Index: 1236577 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1387. Min Act: -0.0000

Data Index: 224035 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1421. Min Act: 0.0000

Data Index: 667951 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1417. Min Act: -0.0000

Data Index: 810379 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1706652 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1461301 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1302. Min Act: 0.0000

Data Index: 1824207 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1334. Min Act: -0.0000

Data Index: 521374 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1318. Min Act: 0.0000

Data Index: 909936 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1311. Min Act: 0.0000

Data Index: 655655 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1300. Min Act: 0.0000

Data Index: 45375 (The Pile)

Max Activating Token Index: 1023