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

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

Neuron 4327 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1406286 (Python Code)

Max Activating Token Index: 451

Text #1

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1557318 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1532222 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1642574 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1532672 (Python Code)

Max Activating Token Index: 613

Text #5

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1576317 (Python Code)

Max Activating Token Index: 851

Text #6

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1551181 (Python Code)

Max Activating Token Index: 364

Text #7

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1379326 (Python Code)

Max Activating Token Index: 560

Text #8

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1621571 (Python Code)

Max Activating Token Index: 1011

Text #9

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1601279 (Python Code)

Max Activating Token Index: 585

Text #10

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1636159 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1490642 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1603895 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1582134 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1435819 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1404209 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1486455 (Python Code)

Max Activating Token Index: 959

Text #17

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1399924 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1595576 (Python Code)

Max Activating Token Index: 664

Text #19

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1368473 (Python Code)

Max Activating Token Index: 732