Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 334 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.2460. Min Act: -0.0002

Data Index: 1407715 (Python Code)

Max Activating Token Index: 522

Text #1

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.2429. Min Act: -0.0002

Data Index: 1495989 (Python Code)

Max Activating Token Index: 513

Text #2

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.2192. Min Act: -0.0002

Data Index: 1603072 (Python Code)

Max Activating Token Index: 805

Text #3

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.2242. Min Act: -0.0002

Data Index: 1598501 (Python Code)

Max Activating Token Index: 624

Text #4

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.2209. Min Act: -0.0002

Data Index: 1572751 (Python Code)

Max Activating Token Index: 518

Text #5

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1967. Min Act: -0.0002

Data Index: 1360193 (Python Code)

Max Activating Token Index: 668

Text #6

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.2306. Min Act: -0.0002

Data Index: 1419026 (Python Code)

Max Activating Token Index: 943

Text #7

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.2047. Min Act: -0.0002

Data Index: 1467165 (Python Code)

Max Activating Token Index: 990

Text #8

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1941. Min Act: -0.0002

Data Index: 1422930 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1971. Min Act: -0.0002

Data Index: 1537761 (Python Code)

Max Activating Token Index: 873

Text #10

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1938. Min Act: -0.0002

Data Index: 1535075 (Python Code)

Max Activating Token Index: 964

Text #11

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1918. Min Act: -0.0002

Data Index: 1593326 (Python Code)

Max Activating Token Index: 926

Text #12

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1917. Min Act: -0.0002

Data Index: 1566953 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1981. Min Act: -0.0002

Data Index: 1620091 (Python Code)

Max Activating Token Index: 863

Text #14

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1843. Min Act: -0.0002

Data Index: 1652333 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1824. Min Act: -0.0002

Data Index: 1571544 (Python Code)

Max Activating Token Index: 800

Text #16

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1769. Min Act: -0.0002

Data Index: 1618276 (Python Code)

Max Activating Token Index: 331

Text #17

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1782. Min Act: -0.0002

Data Index: 1513470 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.2047. Min Act: -0.0002

Data Index: 1594870 (Python Code)

Max Activating Token Index: 940

Text #19

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1835. Min Act: -0.0002

Data Index: 1596954 (Python Code)

Max Activating Token Index: 303