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

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

Neuron 3894 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0917. Min Act: -0.0001

Data Index: 620153 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0878. Min Act: -0.0001

Data Index: 292439 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0869. Min Act: -0.0001

Data Index: 133045 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0811. Min Act: -0.0001

Data Index: 534815 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0853. Min Act: -0.0001

Data Index: 454714 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0837. Min Act: -0.0001

Data Index: 148279 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0755. Min Act: -0.0001

Data Index: 523353 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0738. Min Act: -0.0001

Data Index: 439833 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0778. Min Act: -0.0001

Data Index: 325724 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0751. Min Act: -0.0001

Data Index: 801110 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1234834 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0725. Min Act: -0.0001

Data Index: 892308 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0717. Min Act: -0.0001

Data Index: 600325 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0715. Min Act: -0.0001

Data Index: 165712 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1290014 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0679. Min Act: -0.0001

Data Index: 997121 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0629. Min Act: -0.0001

Data Index: 763640 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0710. Min Act: -0.0001

Data Index: 690388 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0704. Min Act: -0.0001

Data Index: 777451 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0730. Min Act: -0.0001

Data Index: 612780 (C4 (Web Text))

Max Activating Token Index: 752