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

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

Neuron 507 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: -0.0003

Data Index: 350595 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0856. Min Act: -0.0003

Data Index: 396017 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0841. Min Act: -0.0003

Data Index: 275075 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0792. Min Act: -0.0003

Data Index: 1299121 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0829. Min Act: -0.0003

Data Index: 10876 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0819. Min Act: -0.0003

Data Index: 1350769 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0825. Min Act: -0.0003

Data Index: 147796 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0825. Min Act: -0.0003

Data Index: 336391 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0816. Min Act: -0.0003

Data Index: 710429 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0819. Min Act: -0.0003

Data Index: 1014080 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1039605 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0797. Min Act: -0.0003

Data Index: 849213 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0785. Min Act: -0.0003

Data Index: 58229 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1268171 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0830. Min Act: -0.0003

Data Index: 68003 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0782. Min Act: -0.0003

Data Index: 634254 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1008578 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1139945 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0761. Min Act: -0.0003

Data Index: 68686 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0799. Min Act: -0.0003

Data Index: 1217826 (C4 (Web Text))

Max Activating Token Index: 531