Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 721 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.2167. Min Act: -0.0001

Data Index: 508602 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1931. Min Act: -0.0001

Data Index: 151673 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1617. Min Act: -0.0001

Data Index: 466848 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1087786 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1507. Min Act: -0.0001

Data Index: 734240 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1555. Min Act: -0.0001

Data Index: 37595 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1424. Min Act: -0.0001

Data Index: 908304 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1448. Min Act: -0.0001

Data Index: 55434 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1491. Min Act: -0.0001

Data Index: 519622 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1153826 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1324. Min Act: -0.0001

Data Index: 547567 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1326. Min Act: -0.0001

Data Index: 463961 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1367. Min Act: -0.0001

Data Index: 999724 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1174. Min Act: -0.0001

Data Index: 700001 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1397. Min Act: -0.0001

Data Index: 799484 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1203321 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1097722 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1111561 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1216. Min Act: -0.0001

Data Index: 60816 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1194. Min Act: -0.0001

Data Index: 941937 (C4 (Web Text))

Max Activating Token Index: 109