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

Dataset: The Pile

Neuron 3717 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: 0.1386. Min Range: -0.1386

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1645257 (The Pile)

Max Activating Token Index: 968

Text #1

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1300. Min Act: -0.0000

Data Index: 653225 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1675602 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1371065 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1168. Min Act: -0.0000

Data Index: 427913 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1217. Min Act: -0.0000

Data Index: 135826 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1212. Min Act: -0.0000

Data Index: 351439 (The Pile)

Max Activating Token Index: 262

Text #7

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1056622 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1115. Min Act: -0.0000

Data Index: 396235 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1194. Min Act: -0.0000

Data Index: 208325 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1837437 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1047. Min Act: -0.0000

Data Index: 741833 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1310138 (The Pile)

Max Activating Token Index: 367

Text #13

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1228817 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1614020 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1655479 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1019. Min Act: -0.0000

Data Index: 44224 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0944. Min Act: -0.0000

Data Index: 455869 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1988842 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1816740 (The Pile)

Max Activating Token Index: 691