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

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

Neuron 5036 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2792. Min Act: -0.0001

Data Index: 1216008 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1350428 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1953. Min Act: -0.0001

Data Index: 307792 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1864. Min Act: -0.0001

Data Index: 493164 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1693. Min Act: -0.0001

Data Index: 774458 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1722. Min Act: -0.0001

Data Index: 408272 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1724. Min Act: -0.0001

Data Index: 1196316 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1333231 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1491. Min Act: -0.0001

Data Index: 570492 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1598. Min Act: -0.0001

Data Index: 61132 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1702. Min Act: -0.0000

Data Index: 926306 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1122703 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1174408 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1515. Min Act: -0.0001

Data Index: 284671 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1405. Min Act: -0.0001

Data Index: 963977 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1361. Min Act: -0.0001

Data Index: 393740 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1058920 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1280. Min Act: -0.0001

Data Index: 681415 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1209439 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.1217. Min Act: -0.0000

Data Index: 648801 (C4 (Web Text))

Max Activating Token Index: 233