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

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

Neuron 590 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1459576 (Python Code)

Max Activating Token Index: 675

Text #1

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1554751 (Python Code)

Max Activating Token Index: 904

Text #2

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1548612 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1569477 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1369624 (Python Code)

Max Activating Token Index: 958

Text #5

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1633309 (Python Code)

Max Activating Token Index: 338

Text #6

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1596591 (Python Code)

Max Activating Token Index: 185

Text #7

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2221. Min Act: 0.0000

Data Index: 1539413 (Python Code)

Max Activating Token Index: 523

Text #8

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1542722 (Python Code)

Max Activating Token Index: 414

Text #9

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2174. Min Act: 0.0000

Data Index: 1520303 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1537412 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2079. Min Act: 0.0000

Data Index: 1369254 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1908. Min Act: -0.0000

Data Index: 377639 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1631893 (Python Code)

Max Activating Token Index: 911

Text #14

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2005. Min Act: 0.0000

Data Index: 1562171 (Python Code)

Max Activating Token Index: 612

Text #15

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1644646 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1996. Min Act: 0.0000

Data Index: 1490690 (Python Code)

Max Activating Token Index: 905

Text #17

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1416968 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1943. Min Act: 0.0000

Data Index: 1452285 (Python Code)

Max Activating Token Index: 864

Text #19

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1921. Min Act: 0.0000

Data Index: 1380678 (Python Code)

Max Activating Token Index: 329