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

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

Neuron 3586 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1552904 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1554186 (Python Code)

Max Activating Token Index: 572

Text #2

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1491332 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1503930 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1397813 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1461208 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1628895 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1561163 (Python Code)

Max Activating Token Index: 503

Text #8

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1454485 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1493358 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1451838 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1398192 (Python Code)

Max Activating Token Index: 865

Text #12

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1547334 (Python Code)

Max Activating Token Index: 99

Text #13

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1623169 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1934. Min Act: -0.0000

Data Index: 1609465 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1434874 (Python Code)

Max Activating Token Index: 559

Text #16

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1493765 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1582403 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1365346 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1368072 (Python Code)

Max Activating Token Index: 260