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

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

Neuron 2794 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: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1025329 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0708. Min Act: -0.0000

Data Index: 929357 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1146280 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0733. Min Act: -0.0000

Data Index: 840830 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0627. Min Act: -0.0000

Data Index: 471313 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0651. Min Act: -0.0000

Data Index: 136924 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0626. Min Act: -0.0000

Data Index: 447054 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1310310 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0595. Min Act: -0.0000

Data Index: 917960 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1193843 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0614. Min Act: -0.0000

Data Index: 213179 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1319876 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0552. Min Act: -0.0000

Data Index: 837961 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0585. Min Act: -0.0000

Data Index: 896090 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1207509 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0544. Min Act: -0.0000

Data Index: 912027 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1076096 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0535. Min Act: -0.0000

Data Index: 191656 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0530. Min Act: -0.0000

Data Index: 25332 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0524. Min Act: -0.0000

Data Index: 322436 (C4 (Web Text))

Max Activating Token Index: 539