Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2063 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1090582 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0001

Data Index: 596675 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1201550 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1280. Min Act: -0.0001

Data Index: 677389 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1192347 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1025011 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1176. Min Act: -0.0001

Data Index: 640817 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1003292 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1026740 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1093. Min Act: -0.0001

Data Index: 136735 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1126. Min Act: -0.0001

Data Index: 232697 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1085. Min Act: -0.0001

Data Index: 494559 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1064. Min Act: -0.0001

Data Index: 443574 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1092. Min Act: -0.0001

Data Index: 799997 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1113. Min Act: -0.0001

Data Index: 518668 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0999. Min Act: -0.0001

Data Index: 891544 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0994. Min Act: -0.0001

Data Index: 621713 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1164464 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0998. Min Act: -0.0001

Data Index: 17417 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0945. Min Act: -0.0001

Data Index: 33209 (C4 (Web Text))

Max Activating Token Index: 168