Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2610 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1364. Min Act: -0.0000

Data Index: 323555 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1202. Min Act: 0.0000

Data Index: 497557 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1148. Min Act: -0.0000

Data Index: 387294 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1135. Min Act: -0.0000

Data Index: 782371 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1200. Min Act: -0.0000

Data Index: 62617 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1150. Min Act: -0.0000

Data Index: 796741 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1185. Min Act: -0.0000

Data Index: 108155 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1096. Min Act: -0.0000

Data Index: 67679 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1140048 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1167. Min Act: 0.0000

Data Index: 1206898 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1038564 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1118. Min Act: -0.0000

Data Index: 90726 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1152. Min Act: 0.0000

Data Index: 1212797 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1054. Min Act: -0.0000

Data Index: 41476 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1046. Min Act: -0.0000

Data Index: 34709 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1033. Min Act: -0.0000

Data Index: 432102 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1050. Min Act: -0.0000

Data Index: 845261 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1048. Min Act: -0.0000

Data Index: 570514 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1053. Min Act: -0.0000

Data Index: 671703 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1086. Min Act: 0.0000

Data Index: 787953 (C4 (Web Text))

Max Activating Token Index: 830