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

Dataset: The Pile

Neuron 3526 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: 0.1381. Min Range: -0.1381

Max Act: 0.1255. Min Act: -0.0000

Data Index: 541510 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1825856 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1206. Min Act: -0.0000

Data Index: 821668 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1179371 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1294753 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1161. Min Act: -0.0000

Data Index: 691954 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1783408 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1086392 (The Pile)

Max Activating Token Index: 565

Text #8

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1286363 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1782212 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1148. Min Act: -0.0000

Data Index: 822442 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1087. Min Act: -0.0000

Data Index: 278935 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1141. Min Act: -0.0000

Data Index: 726153 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1659331 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1068. Min Act: -0.0000

Data Index: 35352 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1115308 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1558403 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1477351 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0929. Min Act: -0.0000

Data Index: 201589 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1574509 (The Pile)

Max Activating Token Index: 83