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

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

Neuron 3975 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0003

Data Index: 615846 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1527. Min Act: -0.0002

Data Index: 287682 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1524. Min Act: -0.0002

Data Index: 234894 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1523. Min Act: -0.0002

Data Index: 1098905 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1482. Min Act: -0.0002

Data Index: 725355 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1480. Min Act: -0.0002

Data Index: 1239315 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1487. Min Act: -0.0002

Data Index: 867725 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1449. Min Act: -0.0002

Data Index: 703190 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1437. Min Act: -0.0002

Data Index: 866344 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1435. Min Act: -0.0002

Data Index: 503766 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1434. Min Act: -0.0003

Data Index: 430033 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1421. Min Act: -0.0003

Data Index: 790996 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1425. Min Act: -0.0002

Data Index: 745505 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1417. Min Act: -0.0002

Data Index: 637588 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1406. Min Act: -0.0002

Data Index: 968179 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1391. Min Act: -0.0002

Data Index: 405763 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1402. Min Act: -0.0002

Data Index: 961177 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1364. Min Act: -0.0002

Data Index: 664100 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1369. Min Act: -0.0002

Data Index: 169045 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1388. Min Act: -0.0002

Data Index: 1359266 (C4 (Web Text))

Max Activating Token Index: 216