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

Dataset: The Pile

Neuron 3881 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1208290 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1433766 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1665. Min Act: -0.0000

Data Index: 876306 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1564340 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1565464 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1629. Min Act: -0.0000

Data Index: 650624 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1154720 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1511. Min Act: -0.0000

Data Index: 265067 (The Pile)

Max Activating Token Index: 971

Text #8

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1571. Min Act: -0.0000

Data Index: 994405 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1566041 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1520. Min Act: -0.0000

Data Index: 461632 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1602. Min Act: -0.0000

Data Index: 92935 (The Pile)

Max Activating Token Index: 615

Text #12

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1626481 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1394. Min Act: -0.0000

Data Index: 649895 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1322290 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1175262 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1423. Min Act: -0.0000

Data Index: 603850 (The Pile)

Max Activating Token Index: 325

Text #17

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1472. Min Act: -0.0000

Data Index: 376591 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1912091 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1056298 (The Pile)

Max Activating Token Index: 78