Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2333 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1580. Min Act: -0.0003

Data Index: 820089 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0003

Data Index: 372568 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1674. Min Act: -0.0003

Data Index: 859086 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1641. Min Act: -0.0003

Data Index: 632607 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1642. Min Act: -0.0003

Data Index: 45130 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1467. Min Act: -0.0003

Data Index: 622185 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1457. Min Act: -0.0003

Data Index: 734938 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1378. Min Act: -0.0003

Data Index: 722638 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1515. Min Act: -0.0003

Data Index: 225123 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1392. Min Act: -0.0003

Data Index: 145962 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1485. Min Act: -0.0003

Data Index: 1249110 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1383. Min Act: -0.0003

Data Index: 663612 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1467. Min Act: -0.0003

Data Index: 375051 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1370. Min Act: -0.0003

Data Index: 1273005 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1369. Min Act: -0.0003

Data Index: 641207 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1409. Min Act: -0.0003

Data Index: 270746 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1403. Min Act: -0.0003

Data Index: 914504 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1405. Min Act: -0.0003

Data Index: 1102299 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1340. Min Act: -0.0003

Data Index: 749352 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1434. Min Act: -0.0003

Data Index: 167025 (C4 (Web Text))

Max Activating Token Index: 304