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

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

Neuron 3184 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2577. Min Act: -0.0001

Data Index: 1650431 (Python Code)

Max Activating Token Index: 732

Text #1

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1626239 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2577. Min Act: -0.0001

Data Index: 1494022 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1501417 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1382706 (Python Code)

Max Activating Token Index: 543

Text #5

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1578809 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1452197 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1474782 (Python Code)

Max Activating Token Index: 685

Text #8

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1625602 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2211. Min Act: -0.0001

Data Index: 1465831 (Python Code)

Max Activating Token Index: 153

Text #10

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1498117 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1416054 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2222. Min Act: -0.0001

Data Index: 1559610 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2171. Min Act: -0.0001

Data Index: 1478049 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1596632 (Python Code)

Max Activating Token Index: 59

Text #15

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2245. Min Act: -0.0001

Data Index: 1371658 (Python Code)

Max Activating Token Index: 156

Text #16

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2133. Min Act: -0.0001

Data Index: 1610532 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1451150 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1490209 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2030. Min Act: -0.0001

Data Index: 1487013 (Python Code)

Max Activating Token Index: 14