Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4945 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1522667 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1562998 (Python Code)

Max Activating Token Index: 805

Text #2

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1474597 (Python Code)

Max Activating Token Index: 80

Text #3

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1645419 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1465762 (Python Code)

Max Activating Token Index: 881

Text #5

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1533206 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1567405 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1537080 (Python Code)

Max Activating Token Index: 503

Text #8

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1430230 (Python Code)

Max Activating Token Index: 259

Text #9

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1628449 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1573462 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1591416 (Python Code)

Max Activating Token Index: 938

Text #12

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1461923 (Python Code)

Max Activating Token Index: 568

Text #13

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1463162 (Python Code)

Max Activating Token Index: 737

Text #14

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1432352 (Python Code)

Max Activating Token Index: 572

Text #15

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1479193 (Python Code)

Max Activating Token Index: 787

Text #16

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1382524 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1549797 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1376355 (Python Code)

Max Activating Token Index: 651

Text #19

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1554997 (Python Code)

Max Activating Token Index: 845