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

Dataset: The Pile

Neuron 4648 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: 0.2844. Min Range: -0.2844

Max Act: 0.2844. Min Act: -0.0000

Data Index: 227301 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1378352 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2108. Min Act: -0.0000

Data Index: 798425 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1924. Min Act: -0.0000

Data Index: 924168 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1809. Min Act: -0.0000

Data Index: 159790 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1908501 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1776651 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1916184 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1737. Min Act: -0.0000

Data Index: 451931 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1743. Min Act: -0.0000

Data Index: 247774 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1107292 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1286479 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1142680 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1589. Min Act: -0.0000

Data Index: 718538 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1634. Min Act: -0.0000

Data Index: 501366 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1570. Min Act: -0.0000

Data Index: 567758 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1516. Min Act: -0.0000

Data Index: 262447 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1821189 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1086415 (The Pile)

Max Activating Token Index: 642

Text #19

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1651566 (The Pile)

Max Activating Token Index: 1008