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

Dataset: The Pile

Neuron 3672 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.4854. Min Act: -0.0000

Data Index: 488209 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.3122. Min Act: -0.0000

Data Index: 1446756 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1875684 (The Pile)

Max Activating Token Index: 211

Text #3

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2392. Min Act: -0.0000

Data Index: 96361 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2244. Min Act: -0.0000

Data Index: 1954189 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1262174 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2041. Min Act: 0.0000

Data Index: 509190 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1012. Min Act: -0.0000

Data Index: 229359 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1470243 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 1.4854. Min Range: -1.4854

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1070163 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1166813 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0022. Min Act: -0.0000

Data Index: 1077990 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1070656 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 1.4854. Min Range: -1.4854

Max Act: 0.9355. Min Act: -0.0000

Data Index: 667994 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 1.4854. Min Range: -1.4854

Max Act: 0.9551. Min Act: -0.0000

Data Index: 394764 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 1.4854. Min Range: -1.4854

Max Act: 0.9792. Min Act: -0.0000

Data Index: 623444 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0046. Min Act: -0.0000

Data Index: 998311 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 1.4854. Min Range: -1.4854

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1710089 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 1.4854. Min Range: -1.4854

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1301032 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1140690 (The Pile)

Max Activating Token Index: 227