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

Dataset: The Pile

Neuron 1612 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: 0.1686. Min Range: -0.1686

Max Act: 0.1500. Min Act: -0.0000

Data Index: 643227 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1956651 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1519. Min Act: -0.0000

Data Index: 4570 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1347852 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1589870 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1585. Min Act: -0.0000

Data Index: 985642 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1574. Min Act: -0.0000

Data Index: 592109 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1412. Min Act: -0.0000

Data Index: 885683 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1079476 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1443. Min Act: -0.0000

Data Index: 950842 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1112766 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1642. Min Act: -0.0000

Data Index: 751767 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1841467 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1367. Min Act: -0.0000

Data Index: 28901 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1282. Min Act: -0.0000

Data Index: 882157 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1622637 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1492. Min Act: -0.0000

Data Index: 113185 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1197476 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1266. Min Act: -0.0000

Data Index: 572202 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1658137 (The Pile)

Max Activating Token Index: 662