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

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

Neuron 753 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1113017 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1514. Min Act: -0.0000

Data Index: 564109 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1605. Min Act: -0.0000

Data Index: 251124 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1141571 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1490467 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1139302 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1522. Min Act: -0.0000

Data Index: 796905 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1529. Min Act: -0.0000

Data Index: 119406 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1160648 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1371. Min Act: -0.0000

Data Index: 695526 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1309674 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1536914 (Python Code)

Max Activating Token Index: 997

Text #12

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1436. Min Act: -0.0000

Data Index: 633862 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1035614 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1005778 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1274. Min Act: -0.0000

Data Index: 709232 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1311. Min Act: -0.0000

Data Index: 846988 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1334. Min Act: -0.0000

Data Index: 378741 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1342659 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1372. Min Act: -0.0000

Data Index: 959001 (C4 (Web Text))

Max Activating Token Index: 504