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

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

Neuron 3576 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: 1.3237. Min Range: -1.3237

Max Act: 1.3211. Min Act: -0.0001

Data Index: 18341 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.2625. Min Act: -0.0001

Data Index: 574305 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.3237. Min Act: -0.0001

Data Index: 516863 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.3130. Min Act: -0.0001

Data Index: 485380 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.2342. Min Act: -0.0001

Data Index: 120387 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1775. Min Act: -0.0001

Data Index: 242125 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1817. Min Act: -0.0001

Data Index: 924619 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.2120. Min Act: -0.0001

Data Index: 1128763 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.2069. Min Act: -0.0001

Data Index: 1282517 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1898. Min Act: -0.0001

Data Index: 132697 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.2260. Min Act: -0.0001

Data Index: 670387 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1899. Min Act: -0.0001

Data Index: 340233 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1362. Min Act: -0.0001

Data Index: 34479 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1650. Min Act: -0.0001

Data Index: 961249 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1627. Min Act: -0.0001

Data Index: 287423 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1623. Min Act: -0.0001

Data Index: 1332681 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1284. Min Act: -0.0001

Data Index: 865916 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1800. Min Act: -0.0001

Data Index: 788432 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1746. Min Act: -0.0001

Data Index: 1026357 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.3237. Min Range: -1.3237

Max Act: 1.1336. Min Act: -0.0001

Data Index: 322642 (C4 (Web Text))

Max Activating Token Index: 923