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

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

Neuron 2521 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0747. Min Act: -0.0000

Data Index: 236345 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1570631 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0715. Min Act: -0.0000

Data Index: 373937 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1189382 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1212900 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1063191 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0674. Min Act: -0.0000

Data Index: 245989 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0680. Min Act: -0.0000

Data Index: 774120 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0625. Min Act: -0.0001

Data Index: 771121 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1182004 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0580. Min Act: -0.0000

Data Index: 876913 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1450489 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1036314 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0602. Min Act: -0.0000

Data Index: 221890 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0563. Min Act: -0.0000

Data Index: 1316249 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1146901 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1164895 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0596. Min Act: -0.0001

Data Index: 519900 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1144319 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0574. Min Act: -0.0000

Data Index: 217310 (C4 (Web Text))

Max Activating Token Index: 896