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

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

Neuron 2165 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: 1.2106. Min Range: -1.2106

Max Act: 1.1528. Min Act: -0.0000

Data Index: 504189 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 1.2106. Min Range: -1.2106

Max Act: 1.2106. Min Act: -0.0000

Data Index: 78777 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9492. Min Act: -0.0000

Data Index: 661496 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 1.2106. Min Range: -1.2106

Max Act: 1.0057. Min Act: -0.0000

Data Index: 750091 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.2106. Min Range: -1.2106

Max Act: 1.0505. Min Act: -0.0000

Data Index: 111015 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9243. Min Act: -0.0000

Data Index: 100561 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9780. Min Act: -0.0000

Data Index: 522776 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9641. Min Act: -0.0000

Data Index: 679747 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9561. Min Act: -0.0000

Data Index: 192164 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1334503 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1121514 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9499. Min Act: -0.0000

Data Index: 913460 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9423. Min Act: -0.0000

Data Index: 212648 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1215183 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1185122 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9185. Min Act: -0.0000

Data Index: 992812 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9220. Min Act: -0.0000

Data Index: 928000 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9027. Min Act: -0.0000

Data Index: 772892 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1065164 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8972. Min Act: -0.0000

Data Index: 633723 (C4 (Web Text))

Max Activating Token Index: 607