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

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

Neuron 4652 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1817. Min Act: -0.0001

Data Index: 1308775 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1717. Min Act: -0.0001

Data Index: 1058755 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1874. Min Act: -0.0001

Data Index: 323690 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1650. Min Act: -0.0001

Data Index: 307729 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1540. Min Act: -0.0001

Data Index: 780227 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1583. Min Act: -0.0001

Data Index: 1456315 (Python Code)

Max Activating Token Index: 574

Text #6

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1390. Min Act: -0.0001

Data Index: 876992 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1378. Min Act: -0.0001

Data Index: 526790 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1463. Min Act: -0.0001

Data Index: 279089 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1564. Min Act: -0.0001

Data Index: 821912 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1383657 (Python Code)

Max Activating Token Index: 169

Text #11

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1606. Min Act: -0.0001

Data Index: 1101905 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1124182 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1120792 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1506. Min Act: -0.0001

Data Index: 713475 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1244. Min Act: -0.0001

Data Index: 196234 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1524536 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1386582 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1470. Min Act: -0.0001

Data Index: 696860 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.1874. Min Range: -0.1874

Max Act: 0.1407. Min Act: -0.0001

Data Index: 526428 (C4 (Web Text))

Max Activating Token Index: 813