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

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

Neuron 2068 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.6327. Min Act: -0.0000

Data Index: 1387381 (Python Code)

Max Activating Token Index: 396

Text #1

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1507864 (Python Code)

Max Activating Token Index: 342

Text #2

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1573111 (Python Code)

Max Activating Token Index: 250

Text #3

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1437370 (Python Code)

Max Activating Token Index: 578

Text #4

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1603141 (Python Code)

Max Activating Token Index: 203

Text #5

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1624686 (Python Code)

Max Activating Token Index: 965

Text #6

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1486705 (Python Code)

Max Activating Token Index: 876

Text #7

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1644871 (Python Code)

Max Activating Token Index: 253

Text #8

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1411942 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1579520 (Python Code)

Max Activating Token Index: 827

Text #10

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1496934 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1385306 (Python Code)

Max Activating Token Index: 937

Text #12

Max Range: 1.6327. Min Range: -1.6327

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1406759 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1649867 (Python Code)

Max Activating Token Index: 408

Text #14

Max Range: 1.6327. Min Range: -1.6327

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1378185 (Python Code)

Max Activating Token Index: 1022

Text #15

Max Range: 1.6327. Min Range: -1.6327

Max Act: 1.0005. Min Act: -0.0000

Data Index: 1537713 (Python Code)

Max Activating Token Index: 621

Text #16

Max Range: 1.6327. Min Range: -1.6327

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1433605 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 1.6327. Min Range: -1.6327

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1526535 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 1.6327. Min Range: -1.6327

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1582606 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 1.6327. Min Range: -1.6327

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1400697 (Python Code)

Max Activating Token Index: 588