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

Dataset: The Pile

Neuron 1466 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1990. Min Act: -0.0000

Data Index: 8341 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1947049 (The Pile)

Max Activating Token Index: 763

Text #2

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1750. Min Act: -0.0000

Data Index: 254903 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1876068 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1597. Min Act: -0.0000

Data Index: 268192 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1683. Min Act: -0.0000

Data Index: 449262 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1894698 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1491. Min Act: -0.0000

Data Index: 153267 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1570. Min Act: -0.0000

Data Index: 537073 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1540. Min Act: -0.0000

Data Index: 821693 (The Pile)

Max Activating Token Index: 695

Text #10

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1477. Min Act: -0.0000

Data Index: 204718 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1465. Min Act: -0.0000

Data Index: 602849 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1074204 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1429. Min Act: -0.0000

Data Index: 121343 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1427. Min Act: -0.0000

Data Index: 769634 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1718827 (The Pile)

Max Activating Token Index: 352

Text #16

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1782691 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1407021 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1880999 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1621725 (The Pile)

Max Activating Token Index: 819