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

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

Neuron 3517 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.9680. Min Act: -0.0000

Data Index: 1407001 (Python Code)

Max Activating Token Index: 971

Text #1

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.6889. Min Act: -0.0000

Data Index: 1650454 (Python Code)

Max Activating Token Index: 801

Text #2

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.5481. Min Act: -0.0000

Data Index: 1453915 (Python Code)

Max Activating Token Index: 457

Text #3

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1407898 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1485906 (Python Code)

Max Activating Token Index: 596

Text #5

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.4338. Min Act: -0.0000

Data Index: 1574981 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1525244 (Python Code)

Max Activating Token Index: 987

Text #7

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.2791. Min Act: -0.0000

Data Index: 1382570 (Python Code)

Max Activating Token Index: 669

Text #8

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.1405. Min Act: -0.0000

Data Index: 1513864 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1410965 (Python Code)

Max Activating Token Index: 143

Text #10

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.1885. Min Act: -0.0000

Data Index: 1477533 (Python Code)

Max Activating Token Index: 511

Text #11

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1474225 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1474149 (Python Code)

Max Activating Token Index: 174

Text #13

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1507881 (Python Code)

Max Activating Token Index: 266

Text #14

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.2084. Min Act: -0.0000

Data Index: 1389385 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.0828. Min Act: -0.0000

Data Index: 1433739 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1486288 (Python Code)

Max Activating Token Index: 354

Text #17

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1427088 (Python Code)

Max Activating Token Index: 365

Text #18

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1586731 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 1.9680. Min Range: -1.9680

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1596978 (Python Code)

Max Activating Token Index: 862