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

Dataset: The Pile

Neuron 4451 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: 0.2292. Min Range: -0.2292

Max Act: 0.2292. Min Act: -0.0000

Data Index: 481784 (The Pile)

Max Activating Token Index: 896

Text #1

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1082057 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1275242 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1656. Min Act: -0.0000

Data Index: 48917 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1629806 (The Pile)

Max Activating Token Index: 600

Text #5

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1503. Min Act: -0.0000

Data Index: 918190 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1582346 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1881259 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1775966 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1524. Min Act: -0.0000

Data Index: 312703 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1511. Min Act: -0.0000

Data Index: 425748 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1430885 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1565989 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1458. Min Act: -0.0000

Data Index: 29930 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1469. Min Act: -0.0000

Data Index: 1712983 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1455. Min Act: -0.0000

Data Index: 133380 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1443. Min Act: -0.0000

Data Index: 825412 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1374402 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1302. Min Act: -0.0000

Data Index: 913344 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 0.2292. Min Range: -0.2292

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1675239 (The Pile)

Max Activating Token Index: 1018