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

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

Neuron 3295 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1974. Min Act: -0.0000

Data Index: 54260 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1783. Min Act: -0.0000

Data Index: 102748 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1661. Min Act: -0.0000

Data Index: 748822 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1420823 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1666. Min Act: -0.0000

Data Index: 860144 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1082700 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1365650 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1284604 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1595. Min Act: -0.0000

Data Index: 47156 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1105157 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1506. Min Act: -0.0000

Data Index: 194619 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1585331 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1156549 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1472. Min Act: -0.0000

Data Index: 746474 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1364685 (Python Code)

Max Activating Token Index: 939

Text #15

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1375. Min Act: -0.0000

Data Index: 256269 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1312718 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1259150 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1014798 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.1974. Min Range: -0.1974

Max Act: 0.1353. Min Act: -0.0000

Data Index: 430520 (C4 (Web Text))

Max Activating Token Index: 519