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

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

Neuron 5043 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3837. Min Act: -0.0002

Data Index: 1598464 (Python Code)

Max Activating Token Index: 377

Text #1

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3767. Min Act: -0.0002

Data Index: 1638784 (Python Code)

Max Activating Token Index: 893

Text #2

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.4141. Min Act: -0.0002

Data Index: 1505587 (Python Code)

Max Activating Token Index: 345

Text #3

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.4028. Min Act: -0.0002

Data Index: 1470029 (Python Code)

Max Activating Token Index: 467

Text #4

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3982. Min Act: -0.0002

Data Index: 1476777 (Python Code)

Max Activating Token Index: 382

Text #5

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.4189. Min Act: -0.0002

Data Index: 1599248 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3947. Min Act: -0.0002

Data Index: 1542984 (Python Code)

Max Activating Token Index: 345

Text #7

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3693. Min Act: -0.0002

Data Index: 1395791 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3844. Min Act: -0.0002

Data Index: 1459260 (Python Code)

Max Activating Token Index: 351

Text #9

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3035. Min Act: -0.0002

Data Index: 1559442 (Python Code)

Max Activating Token Index: 351

Text #10

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3622. Min Act: -0.0002

Data Index: 1566407 (Python Code)

Max Activating Token Index: 142

Text #11

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3714. Min Act: -0.0002

Data Index: 1391797 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3421. Min Act: -0.0002

Data Index: 1499006 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3642. Min Act: -0.0002

Data Index: 1376661 (Python Code)

Max Activating Token Index: 450

Text #14

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3392. Min Act: -0.0002

Data Index: 1595223 (Python Code)

Max Activating Token Index: 251

Text #15

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3814. Min Act: -0.0002

Data Index: 1518149 (Python Code)

Max Activating Token Index: 276

Text #16

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.2838. Min Act: -0.0002

Data Index: 1594213 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3663. Min Act: -0.0002

Data Index: 1640979 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3291. Min Act: -0.0002

Data Index: 1569273 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3593. Min Act: -0.0002

Data Index: 1509927 (Python Code)

Max Activating Token Index: 375