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

Dataset: The Pile

Neuron 2243 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: 1.2703. Min Range: -1.2703

Max Act: 1.2575. Min Act: -0.0000

Data Index: 943713 (The Pile)

Max Activating Token Index: 901

Text #1

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.2703. Min Act: -0.0000

Data Index: 1285330 (The Pile)

Max Activating Token Index: 84

Text #2

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1855138 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1878364 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0477. Min Act: -0.0000

Data Index: 485227 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1409664 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0551. Min Act: -0.0000

Data Index: 13128 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0529. Min Act: -0.0000

Data Index: 298682 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1959957 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0560. Min Act: -0.0000

Data Index: 319425 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1647074 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1786924 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1820870 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9774. Min Act: -0.0000

Data Index: 176074 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1552620 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1484075 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1539021 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1639449 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1969308 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1894446 (The Pile)

Max Activating Token Index: 807