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

Dataset: The Pile

Neuron 2674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1686654 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1464791 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1991873 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1156. Min Act: -0.0000

Data Index: 729417 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1489505 (The Pile)

Max Activating Token Index: 414

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1177. Min Act: -0.0000

Data Index: 67324 (The Pile)

Max Activating Token Index: 34

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1810025 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1559595 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1870477 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1512630 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1008. Min Act: -0.0000

Data Index: 961774 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1753475 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1275596 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1118. Min Act: -0.0000

Data Index: 492672 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1755927 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1161601 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1173609 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0872. Min Act: -0.0000

Data Index: 999276 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0973. Min Act: -0.0000

Data Index: 835505 (The Pile)

Max Activating Token Index: 196

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0894. Min Act: -0.0000

Data Index: 570529 (The Pile)

Max Activating Token Index: 949