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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 664 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1984. Min Act: -0.0001

Data Index: 973680 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1992. Min Act: -0.0001

Data Index: 552424 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1346. Min Act: -0.0000

Data Index: 497038 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1304. Min Act: -0.0001

Data Index: 497920 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1340. Min Act: -0.0000

Data Index: 653812 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1297. Min Act: -0.0001

Data Index: 242629 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1238320 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1225. Min Act: -0.0001

Data Index: 559139 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1080603 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1123. Min Act: -0.0001

Data Index: 567251 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1123. Min Act: -0.0001

Data Index: 177201 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1107. Min Act: -0.0000

Data Index: 640358 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1339952 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1066. Min Act: -0.0001

Data Index: 393584 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1077. Min Act: -0.0001

Data Index: 124769 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1103. Min Act: -0.0001

Data Index: 402735 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1104. Min Act: -0.0000

Data Index: 515227 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1156. Min Act: -0.0000

Data Index: 657932 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1194757 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1062. Min Act: -0.0001

Data Index: 593585 (C4 (Web Text))

Max Activating Token Index: 76