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

Dataset: The Pile

Neuron 3995 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.6589. Min Act: -0.0000

Data Index: 1137077 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.5722. Min Act: -0.0000

Data Index: 1269433 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.5518. Min Act: -0.0000

Data Index: 998473 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.4672. Min Act: -0.0000

Data Index: 588892 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1034061 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1868554 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.3020. Min Act: -0.0000

Data Index: 290392 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.2730. Min Act: -0.0000

Data Index: 216066 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.2261. Min Act: -0.0000

Data Index: 156449 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1610768 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1195817 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0811. Min Act: -0.0000

Data Index: 117759 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1086671 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1185. Min Act: -0.0000

Data Index: 1167494 (The Pile)

Max Activating Token Index: 625

Text #14

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1060. Min Act: -0.0000

Data Index: 742158 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1715899 (The Pile)

Max Activating Token Index: 738

Text #16

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1067. Min Act: -0.0000

Data Index: 1741549 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0775. Min Act: -0.0000

Data Index: 108241 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1499126 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0852. Min Act: -0.0000

Data Index: 716852 (The Pile)

Max Activating Token Index: 809