Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4364 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1246850 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1359046 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0636. Min Act: -0.0002

Data Index: 497438 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1287265 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0598. Min Act: -0.0002

Data Index: 12951 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0608. Min Act: -0.0002

Data Index: 204312 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0603. Min Act: -0.0002

Data Index: 37113 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0593. Min Act: -0.0002

Data Index: 943760 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0578. Min Act: -0.0002

Data Index: 989552 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0576. Min Act: -0.0002

Data Index: 684815 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0564. Min Act: -0.0002

Data Index: 894230 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0570. Min Act: -0.0002

Data Index: 581836 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0551. Min Act: -0.0002

Data Index: 784823 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0574. Min Act: -0.0002

Data Index: 669278 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1133469 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0556. Min Act: -0.0002

Data Index: 630255 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1280127 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0551. Min Act: -0.0002

Data Index: 70748 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0549. Min Act: -0.0002

Data Index: 64789 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0549. Min Act: -0.0002

Data Index: 367260 (C4 (Web Text))

Max Activating Token Index: 276