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

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

Neuron 991 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1693. Min Act: -0.0001

Data Index: 970830 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1611. Min Act: -0.0001

Data Index: 178130 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1653. Min Act: -0.0001

Data Index: 903669 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1125369 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1341217 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1170205 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1490. Min Act: -0.0001

Data Index: 81124 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1404. Min Act: -0.0001

Data Index: 489720 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1206193 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1089421 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1450. Min Act: -0.0001

Data Index: 220360 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1340. Min Act: -0.0001

Data Index: 471625 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1042971 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1447. Min Act: -0.0001

Data Index: 169966 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1167. Min Act: -0.0001

Data Index: 355307 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1305135 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1093613 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1385. Min Act: -0.0001

Data Index: 908137 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1091861 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1198089 (C4 (Web Text))

Max Activating Token Index: 108