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

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

Neuron 3708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.2127. Min Act: -0.0000

Data Index: 1647958 (Python Code)

Max Activating Token Index: 864

Text #1

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.1905. Min Act: -0.0000

Data Index: 1633551 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.3292. Min Act: -0.0000

Data Index: 1583012 (Python Code)

Max Activating Token Index: 1004

Text #3

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.2177. Min Act: -0.0000

Data Index: 1466819 (Python Code)

Max Activating Token Index: 860

Text #4

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.5171. Min Act: -0.0000

Data Index: 1486567 (Python Code)

Max Activating Token Index: 951

Text #5

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.3533. Min Act: -0.0000

Data Index: 1634303 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.1631. Min Act: -0.0000

Data Index: 1567218 (Python Code)

Max Activating Token Index: 1017

Text #7

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.1917. Min Act: -0.0000

Data Index: 1471543 (Python Code)

Max Activating Token Index: 962

Text #8

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.1721. Min Act: -0.0000

Data Index: 1627591 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.1317. Min Act: -0.0000

Data Index: 1405101 (Python Code)

Max Activating Token Index: 577

Text #10

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.0975. Min Act: -0.0000

Data Index: 1437283 (Python Code)

Max Activating Token Index: 791

Text #11

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.2565. Min Act: -0.0000

Data Index: 1417031 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 3.5171. Min Range: -3.5171

Max Act: 2.6648. Min Act: -0.0000

Data Index: 1440304 (Python Code)

Max Activating Token Index: 711

Text #13

Max Range: 3.5171. Min Range: -3.5171

Max Act: 2.9381. Min Act: -0.0000

Data Index: 1470324 (Python Code)

Max Activating Token Index: 759

Text #14

Max Range: 3.5171. Min Range: -3.5171

Max Act: 2.9521. Min Act: -0.0000

Data Index: 1522095 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 3.5171. Min Range: -3.5171

Max Act: 2.8023. Min Act: -0.0000

Data Index: 1648103 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.0451. Min Act: -0.0000

Data Index: 1525898 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 3.5171. Min Range: -3.5171

Max Act: 2.9014. Min Act: -0.0000

Data Index: 1388871 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 3.5171. Min Range: -3.5171

Max Act: 2.8723. Min Act: -0.0000

Data Index: 1559600 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 3.5171. Min Range: -3.5171

Max Act: 2.8360. Min Act: -0.0000

Data Index: 1556534 (Python Code)

Max Activating Token Index: 662