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

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

Neuron 3350 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1506224 (Python Code)

Max Activating Token Index: 416

Text #1

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1374133 (Python Code)

Max Activating Token Index: 572

Text #2

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1427258 (Python Code)

Max Activating Token Index: 240

Text #3

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6578. Min Act: -0.0000

Data Index: 413983 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1404227 (Python Code)

Max Activating Token Index: 489

Text #5

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1372878 (Python Code)

Max Activating Token Index: 743

Text #6

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5700. Min Act: -0.0000

Data Index: 25844 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1402535 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1502715 (Python Code)

Max Activating Token Index: 775

Text #9

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1503531 (Python Code)

Max Activating Token Index: 658

Text #10

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5409. Min Act: -0.0000

Data Index: 671771 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1603619 (Python Code)

Max Activating Token Index: 605

Text #12

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5468. Min Act: -0.0000

Data Index: 759818 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1041299 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1377506 (Python Code)

Max Activating Token Index: 458

Text #15

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1494911 (Python Code)

Max Activating Token Index: 393

Text #16

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1455859 (Python Code)

Max Activating Token Index: 854

Text #17

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5195. Min Act: -0.0000

Data Index: 772929 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1386786 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.5189. Min Act: -0.0000

Data Index: 259371 (C4 (Web Text))

Max Activating Token Index: 961