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

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

Neuron 1869 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: 1.3745. Min Range: -1.3745

Max Act: 1.3745. Min Act: -0.0000

Data Index: 184109 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.9391. Min Act: -0.0000

Data Index: 83875 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.9415. Min Act: -0.0000

Data Index: 959459 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.9437. Min Act: -0.0000

Data Index: 213862 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1238914 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1358243 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8664. Min Act: -0.0000

Data Index: 335419 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8629. Min Act: -0.0000

Data Index: 144113 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8187. Min Act: -0.0000

Data Index: 109131 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1179040 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8101. Min Act: -0.0000

Data Index: 301908 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8554. Min Act: -0.0000

Data Index: 954808 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.7761. Min Act: -0.0000

Data Index: 32435 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1052299 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.7984. Min Act: -0.0000

Data Index: 997360 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8203. Min Act: -0.0000

Data Index: 892698 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.7664. Min Act: -0.0000

Data Index: 277816 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.7832. Min Act: -0.0000

Data Index: 681800 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.8604. Min Act: -0.0000

Data Index: 523465 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.3745. Min Range: -1.3745

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1121238 (C4 (Web Text))

Max Activating Token Index: 412