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

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

Neuron 1713 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1416. Min Act: -0.0000

Data Index: 831632 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1230494 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1262800 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1290. Min Act: -0.0000

Data Index: 657093 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1168. Min Act: -0.0000

Data Index: 106899 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1195. Min Act: -0.0000

Data Index: 564581 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1259. Min Act: -0.0000

Data Index: 600855 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1112. Min Act: -0.0000

Data Index: 460379 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1235568 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1163. Min Act: -0.0000

Data Index: 732520 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1112. Min Act: -0.0000

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1101. Min Act: -0.0000

Data Index: 953078 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1087. Min Act: -0.0000

Data Index: 476280 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1153. Min Act: -0.0000

Data Index: 342011 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1142. Min Act: -0.0000

Data Index: 590631 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1035. Min Act: -0.0000

Data Index: 547651 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1079. Min Act: -0.0000

Data Index: 610730 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1275644 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1053. Min Act: -0.0000

Data Index: 492389 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1069. Min Act: -0.0000

Data Index: 363222 (C4 (Web Text))

Max Activating Token Index: 687