Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 120 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1335373 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1319318 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0743. Min Act: -0.0001

Data Index: 815240 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0641. Min Act: -0.0001

Data Index: 863766 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0720. Min Act: -0.0001

Data Index: 119231 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0695. Min Act: -0.0001

Data Index: 656066 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0718. Min Act: -0.0001

Data Index: 273641 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1133122 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0764. Min Act: -0.0001

Data Index: 826311 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0644. Min Act: -0.0001

Data Index: 399338 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1250136 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1346267 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0686. Min Act: -0.0001

Data Index: 458114 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1296604 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0688. Min Act: -0.0001

Data Index: 449237 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1007805 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0725. Min Act: -0.0001

Data Index: 828426 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1293216 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1011646 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0688. Min Act: -0.0001

Data Index: 349589 (C4 (Web Text))

Max Activating Token Index: 708