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

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

Neuron 1476 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: 0.1658. Min Range: -0.1658

Max Act: 0.1617. Min Act: -0.0000

Data Index: 264238 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1092912 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1558. Min Act: -0.0000

Data Index: 682445 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1431. Min Act: -0.0000

Data Index: 791519 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1343. Min Act: -0.0000

Data Index: 107901 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1189087 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1178. Min Act: 0.0000

Data Index: 1110342 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1164. Min Act: -0.0000

Data Index: 101966 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1143. Min Act: -0.0000

Data Index: 814029 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1130. Min Act: -0.0000

Data Index: 448523 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1003712 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1130. Min Act: 0.0000

Data Index: 132790 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1320703 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1023. Min Act: -0.0000

Data Index: 687237 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1082. Min Act: 0.0000

Data Index: 877843 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1035. Min Act: -0.0000

Data Index: 110068 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1069. Min Act: -0.0000

Data Index: 426599 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1000. Min Act: -0.0000

Data Index: 717074 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1032. Min Act: -0.0000

Data Index: 64075 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1130. Min Act: -0.0000

Data Index: 470826 (C4 (Web Text))

Max Activating Token Index: 842