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

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

Neuron 2994 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1546523 (Python Code)

Max Activating Token Index: 637

Text #1

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2517. Min Act: -0.0000

Data Index: 1386901 (Python Code)

Max Activating Token Index: 949

Text #2

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1475569 (Python Code)

Max Activating Token Index: 946

Text #3

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1545813 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2204. Min Act: -0.0001

Data Index: 1641818 (Python Code)

Max Activating Token Index: 965

Text #5

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1651960 (Python Code)

Max Activating Token Index: 87

Text #6

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1461114 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1486752 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1620807 (Python Code)

Max Activating Token Index: 176

Text #9

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1593140 (Python Code)

Max Activating Token Index: 920

Text #10

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1413159 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1577890 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1503159 (Python Code)

Max Activating Token Index: 319

Text #13

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1435862 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1386232 (Python Code)

Max Activating Token Index: 860

Text #15

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1637663 (Python Code)

Max Activating Token Index: 1017

Text #16

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1440323 (Python Code)

Max Activating Token Index: 183

Text #17

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1363065 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1565384 (Python Code)

Max Activating Token Index: 266

Text #19

Max Range: 0.2517. Min Range: -0.2517

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1531226 (Python Code)

Max Activating Token Index: 438