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

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

Neuron 1469 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: 0.2573. Min Range: -0.2573

Max Act: 0.2573. Min Act: -0.0001

Data Index: 493714 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2068. Min Act: -0.0001

Data Index: 1138 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2134. Min Act: -0.0001

Data Index: 116541 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2001. Min Act: -0.0001

Data Index: 539231 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1991. Min Act: -0.0001

Data Index: 938891 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1903. Min Act: -0.0001

Data Index: 928306 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1825. Min Act: -0.0001

Data Index: 963429 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1772. Min Act: -0.0001

Data Index: 243807 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1371870 (Python Code)

Max Activating Token Index: 934

Text #9

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1946. Min Act: -0.0001

Data Index: 237982 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1691. Min Act: -0.0001

Data Index: 450562 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1196442 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1689. Min Act: -0.0001

Data Index: 21693 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1705. Min Act: -0.0001

Data Index: 1271079 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1678. Min Act: -0.0001

Data Index: 917105 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1683. Min Act: -0.0001

Data Index: 960232 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1589. Min Act: -0.0001

Data Index: 49817 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1113322 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1622. Min Act: -0.0001

Data Index: 208133 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1698. Min Act: -0.0001

Data Index: 809766 (C4 (Web Text))

Max Activating Token Index: 345