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

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

Neuron 1079 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5134. Min Act: -0.0000

Data Index: 317811 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.6355. Min Act: -0.0000

Data Index: 52852 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5434. Min Act: -0.0000

Data Index: 1052326 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.6563. Min Act: -0.0001

Data Index: 1220805 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.4864. Min Act: -0.0001

Data Index: 1363935 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.4834. Min Act: -0.0001

Data Index: 1459572 (Python Code)

Max Activating Token Index: 449

Text #6

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.4009. Min Act: -0.0000

Data Index: 1499575 (Python Code)

Max Activating Token Index: 249

Text #7

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.3188. Min Act: -0.0001

Data Index: 1470389 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.2371. Min Act: -0.0001

Data Index: 890951 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.1712. Min Act: -0.0001

Data Index: 526725 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.0682. Min Act: -0.0001

Data Index: 1059554 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1347059 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.1196. Min Act: -0.0001

Data Index: 305210 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.1452. Min Act: -0.0001

Data Index: 1353818 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.1356. Min Act: -0.0000

Data Index: 273627 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.1092. Min Act: -0.0000

Data Index: 216698 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.1237. Min Act: -0.0001

Data Index: 488905 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.0548. Min Act: -0.0001

Data Index: 1548049 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.0869. Min Act: -0.0000

Data Index: 687664 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.0642. Min Act: -0.0000

Data Index: 889855 (C4 (Web Text))

Max Activating Token Index: 685