Model: SoLU Model: 2 Layers, 2944 Neurons per Layer

Dataset: The Pile

Neuron 2744 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')

Text #0

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1943263 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1724. Min Act: -0.0000

Data Index: 382192 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1818630 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1639829 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1146937 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1589116 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1033436 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1540. Min Act: -0.0002

Data Index: 20968 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1531. Min Act: -0.0000

Data Index: 1026305 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1562. Min Act: -0.0000

Data Index: 783161 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1555069 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1456731 (The Pile)

Max Activating Token Index: 24

Text #12

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1534. Min Act: -0.0001

Data Index: 124921 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1604. Min Act: -0.0000

Data Index: 332035 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1905549 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1763711 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1457. Min Act: -0.0000

Data Index: 135058 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1458. Min Act: -0.0000

Data Index: 188321 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1465. Min Act: -0.0000

Data Index: 552453 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1433. Min Act: -0.0000

Data Index: 910742 (The Pile)

Max Activating Token Index: 282