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

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

Neuron 381 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2701. Min Act: -0.0001

Data Index: 1458691 (Python Code)

Max Activating Token Index: 363

Text #1

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1855. Min Act: -0.0001

Data Index: 1546090 (Python Code)

Max Activating Token Index: 220

Text #2

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2549. Min Act: -0.0001

Data Index: 1580783 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2539. Min Act: -0.0001

Data Index: 1524131 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1784. Min Act: -0.0001

Data Index: 1489391 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2182. Min Act: -0.0001

Data Index: 1565603 (Python Code)

Max Activating Token Index: 371

Text #6

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2092. Min Act: -0.0001

Data Index: 1521445 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2021. Min Act: -0.0001

Data Index: 1639156 (Python Code)

Max Activating Token Index: 505

Text #8

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1291. Min Act: -0.0001

Data Index: 1651566 (Python Code)

Max Activating Token Index: 346

Text #9

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1645. Min Act: -0.0001

Data Index: 1385949 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1445. Min Act: -0.0001

Data Index: 1650403 (Python Code)

Max Activating Token Index: 302

Text #11

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1791. Min Act: -0.0001

Data Index: 1428439 (Python Code)

Max Activating Token Index: 785

Text #12

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1262. Min Act: -0.0001

Data Index: 1501348 (Python Code)

Max Activating Token Index: 414

Text #13

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0669. Min Act: -0.0001

Data Index: 1480342 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1523. Min Act: -0.0001

Data Index: 1431911 (Python Code)

Max Activating Token Index: 771

Text #15

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0908. Min Act: -0.0001

Data Index: 1552977 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1217. Min Act: -0.0001

Data Index: 1614932 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0786. Min Act: -0.0001

Data Index: 1452900 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0493. Min Act: -0.0001

Data Index: 1365150 (Python Code)

Max Activating Token Index: 903

Text #19

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1590459 (Python Code)

Max Activating Token Index: 458