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

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

Neuron 3978 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2969. Min Act: -0.0000

Data Index: 434730 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1596119 (Python Code)

Max Activating Token Index: 992

Text #2

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1609886 (Python Code)

Max Activating Token Index: 92

Text #3

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1433740 (Python Code)

Max Activating Token Index: 124

Text #4

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1086334 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2279. Min Act: -0.0000

Data Index: 328734 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1087473 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2360. Min Act: -0.0000

Data Index: 383420 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2184. Min Act: -0.0000

Data Index: 612303 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1291555 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1578961 (Python Code)

Max Activating Token Index: 888

Text #11

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1477670 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2059. Min Act: -0.0000

Data Index: 421217 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2139. Min Act: -0.0000

Data Index: 461787 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1440365 (Python Code)

Max Activating Token Index: 204

Text #15

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1489929 (Python Code)

Max Activating Token Index: 468

Text #16

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2071. Min Act: -0.0000

Data Index: 397870 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1147508 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1991. Min Act: -0.0000

Data Index: 844235 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1105785 (C4 (Web Text))

Max Activating Token Index: 744