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

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

Neuron 3011 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1585977 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.0887. Min Act: -0.0000

Data Index: 653121 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.2031. Min Act: -0.0000

Data Index: 759808 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1241182 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1011580 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1077887 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.1206. Min Act: -0.0000

Data Index: 875749 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.0941. Min Act: -0.0000

Data Index: 980024 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.0988. Min Act: -0.0000

Data Index: 488439 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.1558. Min Act: -0.0000

Data Index: 924147 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1088876 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.0622. Min Act: -0.0000

Data Index: 383024 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.1251. Min Act: -0.0000

Data Index: 1129518 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1139826 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1047234 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.1097. Min Act: -0.0000

Data Index: 900478 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.0582. Min Act: -0.0000

Data Index: 635854 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1328795 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 1.2077. Min Range: -1.2077

Max Act: 1.0126. Min Act: -0.0000

Data Index: 538459 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 1.2077. Min Range: -1.2077

Max Act: 0.9631. Min Act: -0.0000

Data Index: 177106 (C4 (Web Text))

Max Activating Token Index: 1011