Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1479 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1771356 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1585. Min Act: 0.0000

Data Index: 1801267 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1324553 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1453452 (The Pile)

Max Activating Token Index: 831

Text #4

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1548. Min Act: 0.0000

Data Index: 950150 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1687204 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1471. Min Act: 0.0000

Data Index: 549186 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1608. Min Act: -0.0000

Data Index: 848063 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1858583 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1557. Min Act: -0.0000

Data Index: 867681 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1472. Min Act: -0.0000

Data Index: 346503 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1894232 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1555. Min Act: -0.0000

Data Index: 672957 (The Pile)

Max Activating Token Index: 22

Text #13

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1329. Min Act: 0.0000

Data Index: 1482495 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1655006 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1569. Min Act: 0.0000

Data Index: 55702 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1940408 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1312. Min Act: -0.0000

Data Index: 288320 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1451. Min Act: 0.0000

Data Index: 1304489 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1369. Min Act: 0.0000

Data Index: 1499889 (The Pile)

Max Activating Token Index: 953