Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1929. Min Act: -0.0000

Data Index: 915286 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1875. Min Act: -0.0000

Data Index: 854163 (The Pile)

Max Activating Token Index: 346

Text #2

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1584. Min Act: -0.0000

Data Index: 77218 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1596110 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1683. Min Act: -0.0000

Data Index: 254968 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1626. Min Act: -0.0000

Data Index: 144295 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1619. Min Act: -0.0000

Data Index: 765230 (The Pile)

Max Activating Token Index: 143

Text #7

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1676. Min Act: -0.0000

Data Index: 99271 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1675. Min Act: -0.0000

Data Index: 602340 (The Pile)

Max Activating Token Index: 973

Text #9

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1670377 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1475. Min Act: -0.0000

Data Index: 957137 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1624. Min Act: -0.0000

Data Index: 611339 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1021444 (The Pile)

Max Activating Token Index: 796

Text #13

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1441. Min Act: -0.0000

Data Index: 717004 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1293108 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1450. Min Act: -0.0000

Data Index: 563603 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1188787 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1614. Min Act: -0.0000

Data Index: 685764 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1551. Min Act: -0.0000

Data Index: 647940 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1456. Min Act: -0.0000

Data Index: 125508 (The Pile)

Max Activating Token Index: 340