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

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

Neuron 1033 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: 0.2976. Min Range: -0.2976

Max Act: 0.2976. Min Act: -0.0001

Data Index: 1603881 (Python Code)

Max Activating Token Index: 752

Text #1

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2605. Min Act: -0.0001

Data Index: 1382398 (Python Code)

Max Activating Token Index: 91

Text #2

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1514160 (Python Code)

Max Activating Token Index: 837

Text #3

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2277. Min Act: -0.0001

Data Index: 1556985 (Python Code)

Max Activating Token Index: 452

Text #4

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2350. Min Act: -0.0002

Data Index: 1576016 (Python Code)

Max Activating Token Index: 940

Text #5

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1524025 (Python Code)

Max Activating Token Index: 203

Text #6

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2296. Min Act: -0.0002

Data Index: 1548137 (Python Code)

Max Activating Token Index: 778

Text #7

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2232. Min Act: -0.0002

Data Index: 1433530 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2351. Min Act: -0.0001

Data Index: 1406159 (Python Code)

Max Activating Token Index: 461

Text #9

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2177. Min Act: -0.0002

Data Index: 1593512 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2112. Min Act: -0.0002

Data Index: 1509731 (Python Code)

Max Activating Token Index: 857

Text #11

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2178. Min Act: -0.0002

Data Index: 1360701 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2189. Min Act: -0.0002

Data Index: 1517513 (Python Code)

Max Activating Token Index: 900

Text #13

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2136. Min Act: -0.0002

Data Index: 1495730 (Python Code)

Max Activating Token Index: 434

Text #14

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2099. Min Act: -0.0002

Data Index: 1620329 (Python Code)

Max Activating Token Index: 689

Text #15

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2089. Min Act: -0.0002

Data Index: 1533924 (Python Code)

Max Activating Token Index: 871

Text #16

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2146. Min Act: -0.0002

Data Index: 1643999 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2069. Min Act: -0.0002

Data Index: 1544294 (Python Code)

Max Activating Token Index: 765

Text #18

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2106. Min Act: -0.0002

Data Index: 1561185 (Python Code)

Max Activating Token Index: 879

Text #19

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2079. Min Act: -0.0002

Data Index: 1582184 (Python Code)

Max Activating Token Index: 513