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

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

Neuron 2665 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1962. Min Act: -0.0003

Data Index: 801620 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1678. Min Act: -0.0003

Data Index: 243500 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1544. Min Act: -0.0003

Data Index: 1220670 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1529. Min Act: -0.0003

Data Index: 1304515 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1455. Min Act: -0.0002

Data Index: 642584 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1487. Min Act: -0.0003

Data Index: 784106 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1472. Min Act: -0.0003

Data Index: 1142274 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1448. Min Act: -0.0003

Data Index: 1191036 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1433. Min Act: -0.0002

Data Index: 1191470 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1432. Min Act: -0.0003

Data Index: 347434 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1429. Min Act: -0.0003

Data Index: 460002 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1421. Min Act: -0.0002

Data Index: 629249 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1420. Min Act: -0.0003

Data Index: 56102 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1385. Min Act: -0.0002

Data Index: 146671 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1387. Min Act: -0.0003

Data Index: 398909 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1376. Min Act: -0.0003

Data Index: 329195 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1315. Min Act: -0.0003

Data Index: 923231 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1359. Min Act: -0.0003

Data Index: 1189129 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1362. Min Act: -0.0003

Data Index: 1024300 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1346. Min Act: -0.0002

Data Index: 862304 (C4 (Web Text))

Max Activating Token Index: 881