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

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

Neuron 2022 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0003

Data Index: 157428 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0766. Min Act: -0.0003

Data Index: 404290 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0721. Min Act: -0.0003

Data Index: 740895 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0662. Min Act: -0.0003

Data Index: 293349 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0701. Min Act: -0.0003

Data Index: 158321 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1304286 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0635. Min Act: -0.0003

Data Index: 698133 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0661. Min Act: -0.0003

Data Index: 264337 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1318939 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1137321 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0657. Min Act: -0.0003

Data Index: 596762 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0669. Min Act: -0.0003

Data Index: 312574 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0639. Min Act: -0.0003

Data Index: 169656 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0585. Min Act: -0.0003

Data Index: 313768 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0685. Min Act: -0.0003

Data Index: 501678 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0583. Min Act: -0.0003

Data Index: 677542 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0630. Min Act: -0.0003

Data Index: 539331 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0727. Min Act: -0.0003

Data Index: 635746 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0621. Min Act: -0.0003

Data Index: 259811 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0592. Min Act: -0.0004

Data Index: 216709 (C4 (Web Text))

Max Activating Token Index: 909