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

Dataset: The Pile

Neuron 2160 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: 1.3672. Min Range: -1.3672

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1417623 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.3672. Min Act: -0.0000

Data Index: 1638525 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.2876. Min Act: -0.0000

Data Index: 702750 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1531567 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.3535. Min Act: -0.0000

Data Index: 1054084 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.3233. Min Act: -0.0000

Data Index: 688675 (The Pile)

Max Activating Token Index: 122

Text #6

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1749844 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1098398 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.2292. Min Act: -0.0000

Data Index: 1050109 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.1515. Min Act: -0.0000

Data Index: 1221162 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1845058 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1798046 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.1816. Min Act: -0.0000

Data Index: 10604 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1795161 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.1773. Min Act: -0.0000

Data Index: 530308 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1330009 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1673070 (The Pile)

Max Activating Token Index: 994

Text #17

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.0616. Min Act: -0.0000

Data Index: 1214243 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1505141 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 1.3672. Min Range: -1.3672

Max Act: 1.1235. Min Act: -0.0000

Data Index: 845520 (The Pile)

Max Activating Token Index: 984