Model: SoLU Model: 2 Layers, 2944 Neurons per Layer

Dataset: The Pile

Neuron 2341 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')

Text #0

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0002

Data Index: 1888191 (The Pile)

Max Activating Token Index: 14

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1736. Min Act: -0.0001

Data Index: 390310 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1702. Min Act: -0.0001

Data Index: 96374 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1938854 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1523. Min Act: -0.0002

Data Index: 1377914 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1570. Min Act: -0.0002

Data Index: 1929788 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1508. Min Act: -0.0002

Data Index: 137168 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1432. Min Act: -0.0001

Data Index: 754298 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1442. Min Act: -0.0002

Data Index: 1348464 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1118955 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1618791 (The Pile)

Max Activating Token Index: 56

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1405. Min Act: -0.0001

Data Index: 92038 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1802943 (The Pile)

Max Activating Token Index: 8

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1538391 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1776102 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1371. Min Act: -0.0001

Data Index: 752402 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1707168 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1353. Min Act: -0.0001

Data Index: 114926 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1316. Min Act: -0.0002

Data Index: 170701 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1535983 (The Pile)

Max Activating Token Index: 8