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

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

Neuron 3531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1878. Min Act: -0.0001

Data Index: 882302 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1770. Min Act: -0.0000

Data Index: 125626 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1510. Min Act: -0.0001

Data Index: 711253 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1262514 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1110305 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1552. Min Act: -0.0001

Data Index: 586366 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1615. Min Act: -0.0000

Data Index: 790857 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1000217 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1520. Min Act: -0.0001

Data Index: 346236 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1026113 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1478. Min Act: -0.0000

Data Index: 519989 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1495. Min Act: -0.0001

Data Index: 262975 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1116515 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1433. Min Act: -0.0001

Data Index: 771634 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1327646 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1368. Min Act: -0.0001

Data Index: 453734 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1566. Min Act: -0.0000

Data Index: 700571 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1229777 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1450. Min Act: -0.0001

Data Index: 730287 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1197274 (C4 (Web Text))

Max Activating Token Index: 914