Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2235 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0000

Data Index: 216740 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1394747 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1673607 (The Pile)

Max Activating Token Index: 918

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1627172 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1851223 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1504. Min Act: -0.0000

Data Index: 573917 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1367257 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1076592 (The Pile)

Max Activating Token Index: 627

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1349. Min Act: -0.0000

Data Index: 139649 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1113048 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1419. Min Act: -0.0000

Data Index: 680094 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1335. Min Act: -0.0000

Data Index: 37084 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1490. Min Act: -0.0000

Data Index: 710755 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1635996 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1391. Min Act: -0.0000

Data Index: 779273 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1305. Min Act: -0.0000

Data Index: 597519 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1278181 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1931605 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1729070 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1315. Min Act: 0.0001

Data Index: 459347 (The Pile)

Max Activating Token Index: 56