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

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

Neuron 1849 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: 0.1782. Min Range: -0.1782

Max Act: 0.1745. Min Act: -0.0001

Data Index: 454925 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1782. Min Act: -0.0001

Data Index: 979769 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1657. Min Act: -0.0001

Data Index: 111316 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1423. Min Act: -0.0001

Data Index: 846163 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1331. Min Act: -0.0001

Data Index: 190393 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1279. Min Act: -0.0001

Data Index: 611106 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1284401 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1358553 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1284. Min Act: -0.0001

Data Index: 850638 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1163. Min Act: -0.0001

Data Index: 853115 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1202. Min Act: -0.0001

Data Index: 972725 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1028. Min Act: -0.0001

Data Index: 860283 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1241981 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1189. Min Act: -0.0001

Data Index: 920878 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1231. Min Act: -0.0001

Data Index: 33710 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1069. Min Act: -0.0001

Data Index: 907442 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1210256 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1104. Min Act: -0.0001

Data Index: 961661 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1078. Min Act: -0.0001

Data Index: 985008 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1018. Min Act: -0.0001

Data Index: 727517 (C4 (Web Text))

Max Activating Token Index: 317