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

Dataset: The Pile

Neuron 820 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: 1.4830. Min Range: -1.4830

Max Act: 1.4773. Min Act: -0.0000

Data Index: 897036 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4070. Min Act: -0.0000

Data Index: 403547 (The Pile)

Max Activating Token Index: 625

Text #2

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4830. Min Act: -0.0000

Data Index: 1513286 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4697. Min Act: -0.0000

Data Index: 1560429 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3684. Min Act: -0.0000

Data Index: 717569 (The Pile)

Max Activating Token Index: 475

Text #5

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1381894 (The Pile)

Max Activating Token Index: 839

Text #6

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4055. Min Act: -0.0000

Data Index: 693877 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3329. Min Act: -0.0000

Data Index: 1063211 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1022343 (The Pile)

Max Activating Token Index: 982

Text #9

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3821. Min Act: -0.0000

Data Index: 358921 (The Pile)

Max Activating Token Index: 190

Text #10

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3591. Min Act: -0.0000

Data Index: 1948473 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1876713 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1817256 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2901. Min Act: -0.0000

Data Index: 564295 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2856. Min Act: -0.0000

Data Index: 833312 (The Pile)

Max Activating Token Index: 389

Text #15

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2909. Min Act: -0.0000

Data Index: 1283095 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1373087 (The Pile)

Max Activating Token Index: 407

Text #17

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2608. Min Act: -0.0000

Data Index: 1025998 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2664. Min Act: -0.0000

Data Index: 1737448 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1776995 (The Pile)

Max Activating Token Index: 275