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

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

Neuron 3089 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0759. Min Act: -0.0002

Data Index: 202663 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.1016. Min Act: -0.0001

Data Index: 518498 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.1331. Min Act: -0.0001

Data Index: 557805 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0905. Min Act: -0.0001

Data Index: 1179887 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0907. Min Act: -0.0002

Data Index: 637038 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0749. Min Act: -0.0002

Data Index: 545635 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0221. Min Act: -0.0002

Data Index: 1027219 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.1106. Min Act: -0.0001

Data Index: 604604 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0378. Min Act: -0.0001

Data Index: 776165 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.9889. Min Act: -0.0002

Data Index: 1229780 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.9831. Min Act: -0.0002

Data Index: 1166486 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0680. Min Act: -0.0001

Data Index: 1283861 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0009. Min Act: -0.0002

Data Index: 1202015 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.9768. Min Act: -0.0001

Data Index: 618234 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.1685. Min Act: -0.0001

Data Index: 543864 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0249. Min Act: -0.0001

Data Index: 732970 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0008. Min Act: -0.0001

Data Index: 287557 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.0037. Min Act: -0.0002

Data Index: 1253065 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.1127. Min Act: -0.0001

Data Index: 1302459 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.9791. Min Act: -0.0002

Data Index: 907247 (C4 (Web Text))

Max Activating Token Index: 738