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

Dataset: The Pile

Neuron 2656 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: 5.7370. Min Range: -5.7370

Max Act: 5.7370. Min Act: -0.0000

Data Index: 578948 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 5.7370. Min Range: -5.7370

Max Act: 5.2125. Min Act: -0.0000

Data Index: 1756875 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.8272. Min Act: -0.0000

Data Index: 252485 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 5.7370. Min Range: -5.7370

Max Act: 5.0720. Min Act: -0.0001

Data Index: 725600 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.7211. Min Act: -0.0000

Data Index: 804378 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.2753. Min Act: -0.0000

Data Index: 1825117 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.9599. Min Act: -0.0000

Data Index: 163823 (The Pile)

Max Activating Token Index: 894

Text #7

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.3421. Min Act: -0.0000

Data Index: 160410 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.4177. Min Act: -0.0000

Data Index: 642308 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.1655. Min Act: -0.0000

Data Index: 1671250 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.1147. Min Act: -0.0000

Data Index: 173387 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 5.7370. Min Range: -5.7370

Max Act: 3.8547. Min Act: -0.0000

Data Index: 1307753 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.1625. Min Act: -0.0000

Data Index: 1821587 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.4806. Min Act: -0.0000

Data Index: 1504905 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 5.7370. Min Range: -5.7370

Max Act: 3.9597. Min Act: -0.0000

Data Index: 1259102 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 5.7370. Min Range: -5.7370

Max Act: 3.9640. Min Act: -0.0000

Data Index: 1819154 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.1109. Min Act: -0.0000

Data Index: 1351957 (The Pile)

Max Activating Token Index: 50

Text #17

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.0873. Min Act: -0.0000

Data Index: 57846 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.0549. Min Act: -0.0000

Data Index: 897275 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 5.7370. Min Range: -5.7370

Max Act: 4.0605. Min Act: -0.0000

Data Index: 1035687 (The Pile)

Max Activating Token Index: 1022