Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 56 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.3453. Min Act: -0.0001

Data Index: 1547942 (Python Code)

Max Activating Token Index: 54

Text #1

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.2498. Min Act: -0.0001

Data Index: 1406471 (Python Code)

Max Activating Token Index: 89

Text #2

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.1491. Min Act: -0.0001

Data Index: 1628555 (Python Code)

Max Activating Token Index: 367

Text #3

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.1157. Min Act: -0.0001

Data Index: 1482104 (Python Code)

Max Activating Token Index: 453

Text #4

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.1427. Min Act: -0.0001

Data Index: 1572256 (Python Code)

Max Activating Token Index: 273

Text #5

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.1089. Min Act: -0.0001

Data Index: 1568261 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.0674. Min Act: -0.0001

Data Index: 1404212 (Python Code)

Max Activating Token Index: 113

Text #7

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.0394. Min Act: -0.0001

Data Index: 1369760 (Python Code)

Max Activating Token Index: 324

Text #8

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.0901. Min Act: -0.0001

Data Index: 1384073 (Python Code)

Max Activating Token Index: 349

Text #9

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.1156. Min Act: -0.0001

Data Index: 1614272 (Python Code)

Max Activating Token Index: 476

Text #10

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.1892. Min Act: -0.0001

Data Index: 1448725 (Python Code)

Max Activating Token Index: 181

Text #11

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.0408. Min Act: -0.0001

Data Index: 1515144 (Python Code)

Max Activating Token Index: 510

Text #12

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.0009. Min Act: -0.0001

Data Index: 1560637 (Python Code)

Max Activating Token Index: 143

Text #13

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.0550. Min Act: -0.0001

Data Index: 1449075 (Python Code)

Max Activating Token Index: 1013

Text #14

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.0205. Min Act: -0.0001

Data Index: 1441466 (Python Code)

Max Activating Token Index: 486

Text #15

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.0293. Min Act: -0.0001

Data Index: 1620451 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 1.3453. Min Range: -1.3453

Max Act: 0.9658. Min Act: -0.0001

Data Index: 1641619 (Python Code)

Max Activating Token Index: 175

Text #17

Max Range: 1.3453. Min Range: -1.3453

Max Act: 0.8915. Min Act: -0.0001

Data Index: 1639669 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 1.3453. Min Range: -1.3453

Max Act: 0.9918. Min Act: -0.0001

Data Index: 1606446 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 1.3453. Min Range: -1.3453

Max Act: 1.0143. Min Act: -0.0001

Data Index: 1647303 (Python Code)

Max Activating Token Index: 340