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

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

Neuron 2683 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1370395 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1580390 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1580993 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1398032 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1541. Min Act: -0.0001

Data Index: 1429081 (Python Code)

Max Activating Token Index: 39

Text #5

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1555504 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1361957 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1491796 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1508998 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1363311 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1417126 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1582047 (Python Code)

Max Activating Token Index: 316

Text #12

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1449844 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1582481 (Python Code)

Max Activating Token Index: 438

Text #14

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1508996 (Python Code)

Max Activating Token Index: 362

Text #15

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1536169 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1643976 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1627900 (Python Code)

Max Activating Token Index: 176

Text #18

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1611423 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1653758 (Python Code)

Max Activating Token Index: 612