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

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

Neuron 65 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.4253. Min Act: -0.0001

Data Index: 1599161 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.4225. Min Act: -0.0001

Data Index: 1446245 (Python Code)

Max Activating Token Index: 932

Text #2

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2607. Min Act: -0.0001

Data Index: 1495954 (Python Code)

Max Activating Token Index: 899

Text #3

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2278. Min Act: -0.0001

Data Index: 1641132 (Python Code)

Max Activating Token Index: 903

Text #4

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2176. Min Act: -0.0001

Data Index: 1393215 (Python Code)

Max Activating Token Index: 776

Text #5

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2909. Min Act: -0.0001

Data Index: 1423404 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.4389. Min Act: -0.0001

Data Index: 1486451 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2586. Min Act: -0.0001

Data Index: 1477239 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2490. Min Act: -0.0001

Data Index: 1577522 (Python Code)

Max Activating Token Index: 894

Text #9

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.0952. Min Act: -0.0001

Data Index: 1397079 (Python Code)

Max Activating Token Index: 524

Text #10

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.4088. Min Act: -0.0001

Data Index: 1568125 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1059. Min Act: -0.0001

Data Index: 1437825 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2383. Min Act: -0.0001

Data Index: 1652037 (Python Code)

Max Activating Token Index: 692

Text #13

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2231. Min Act: -0.0001

Data Index: 1388809 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.0500. Min Act: -0.0001

Data Index: 1612110 (Python Code)

Max Activating Token Index: 1003

Text #15

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.3302. Min Act: -0.0001

Data Index: 1534758 (Python Code)

Max Activating Token Index: 518

Text #16

Max Range: 3.4389. Min Range: -3.4389

Max Act: 2.7588. Min Act: -0.0001

Data Index: 1558369 (Python Code)

Max Activating Token Index: 1000

Text #17

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1754. Min Act: -0.0001

Data Index: 1597412 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1641. Min Act: -0.0001

Data Index: 1486678 (Python Code)

Max Activating Token Index: 421

Text #19

Max Range: 3.4389. Min Range: -3.4389

Max Act: 2.8850. Min Act: -0.0001

Data Index: 1607635 (Python Code)

Max Activating Token Index: 738