Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3056 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1620869 (Python Code)

Max Activating Token Index: 793

Text #1

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1656133 (Python Code)

Max Activating Token Index: 181

Text #2

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1521309 (Python Code)

Max Activating Token Index: 312

Text #3

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1345476 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1576092 (Python Code)

Max Activating Token Index: 546

Text #5

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1598711 (Python Code)

Max Activating Token Index: 532

Text #6

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1432832 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1400714 (Python Code)

Max Activating Token Index: 249

Text #8

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1499307 (Python Code)

Max Activating Token Index: 1008

Text #9

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1458205 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1518505 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1517038 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1375907 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1513473 (Python Code)

Max Activating Token Index: 334

Text #14

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1509495 (Python Code)

Max Activating Token Index: 699

Text #15

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1373349 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1561556 (Python Code)

Max Activating Token Index: 93

Text #17

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1381777 (Python Code)

Max Activating Token Index: 566

Text #18

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1351. Min Act: -0.0001

Data Index: 1399976 (Python Code)

Max Activating Token Index: 587

Text #19

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1447192 (Python Code)

Max Activating Token Index: 192