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

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

Neuron 4594 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.5866. Min Act: -0.0003

Data Index: 1606551 (Python Code)

Max Activating Token Index: 539

Text #1

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.5018. Min Act: -0.0003

Data Index: 1395549 (Python Code)

Max Activating Token Index: 490

Text #2

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.3554. Min Act: -0.0002

Data Index: 1628592 (Python Code)

Max Activating Token Index: 654

Text #3

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.3450. Min Act: -0.0003

Data Index: 1620121 (Python Code)

Max Activating Token Index: 460

Text #4

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2654. Min Act: -0.0002

Data Index: 1403698 (Python Code)

Max Activating Token Index: 674

Text #5

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2914. Min Act: -0.0003

Data Index: 1518070 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2924. Min Act: -0.0002

Data Index: 1636962 (Python Code)

Max Activating Token Index: 908

Text #7

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.3392. Min Act: -0.0003

Data Index: 1631183 (Python Code)

Max Activating Token Index: 484

Text #8

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.3413. Min Act: -0.0003

Data Index: 1381422 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.3725. Min Act: -0.0003

Data Index: 1623240 (Python Code)

Max Activating Token Index: 544

Text #10

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.3438. Min Act: -0.0003

Data Index: 1573678 (Python Code)

Max Activating Token Index: 906

Text #11

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1912. Min Act: -0.0003

Data Index: 1498431 (Python Code)

Max Activating Token Index: 259

Text #12

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2512. Min Act: -0.0003

Data Index: 1626101 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2244. Min Act: -0.0003

Data Index: 1590893 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2165. Min Act: -0.0002

Data Index: 1571606 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2779. Min Act: -0.0002

Data Index: 1495677 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2475. Min Act: -0.0003

Data Index: 1414853 (Python Code)

Max Activating Token Index: 579

Text #17

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2386. Min Act: -0.0003

Data Index: 1407135 (Python Code)

Max Activating Token Index: 505

Text #18

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.3480. Min Act: -0.0002

Data Index: 1442898 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2650. Min Act: -0.0002

Data Index: 1521893 (Python Code)

Max Activating Token Index: 490