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

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

Neuron 2088 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1196. Min Act: -0.0001

Data Index: 238646 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0966. Min Act: -0.0001

Data Index: 401975 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1003659 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1318598 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1320787 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0817. Min Act: -0.0001

Data Index: 384141 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1265236 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0809. Min Act: -0.0001

Data Index: 379329 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0811. Min Act: -0.0001

Data Index: 578670 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0834. Min Act: -0.0001

Data Index: 64129 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0795. Min Act: -0.0001

Data Index: 938031 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1339023 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0786. Min Act: -0.0001

Data Index: 216514 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0736. Min Act: -0.0001

Data Index: 59767 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1562386 (Python Code)

Max Activating Token Index: 776

Text #15

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1080887 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1169546 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0719. Min Act: -0.0001

Data Index: 620192 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0801. Min Act: -0.0001

Data Index: 553189 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0766. Min Act: -0.0001

Data Index: 546915 (C4 (Web Text))

Max Activating Token Index: 994