Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2354 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.6240. Min Act: -0.0001

Data Index: 1552909 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.6070. Min Act: -0.0001

Data Index: 1555861 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5765. Min Act: -0.0001

Data Index: 1557844 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1503195 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5692. Min Act: -0.0001

Data Index: 1362604 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5428. Min Act: -0.0001

Data Index: 1619465 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1626950 (Python Code)

Max Activating Token Index: 222

Text #7

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5376. Min Act: -0.0001

Data Index: 1455763 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5155. Min Act: -0.0001

Data Index: 1422866 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5379. Min Act: -0.0001

Data Index: 1462119 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5197. Min Act: -0.0001

Data Index: 1570558 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5326. Min Act: -0.0001

Data Index: 1421405 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1395248 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.5198. Min Act: -0.0001

Data Index: 1488927 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4627. Min Act: -0.0001

Data Index: 1397403 (Python Code)

Max Activating Token Index: 598

Text #15

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4894. Min Act: -0.0001

Data Index: 1507589 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4875. Min Act: -0.0001

Data Index: 1552192 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4849. Min Act: -0.0001

Data Index: 1543702 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4671. Min Act: -0.0001

Data Index: 1566730 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4800. Min Act: -0.0001

Data Index: 1591921 (Python Code)

Max Activating Token Index: 10