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

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

Neuron 4160 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1508. Min Range: -2.1508

Max Act: 2.1508. Min Act: -0.0000

Data Index: 529438 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 2.1508. Min Range: -2.1508

Max Act: 2.0153. Min Act: -0.0000

Data Index: 115672 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8411. Min Act: -0.0000

Data Index: 1156019 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7049. Min Act: -0.0000

Data Index: 953945 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5951. Min Act: -0.0000

Data Index: 795053 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.6512. Min Act: -0.0000

Data Index: 302018 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1251131 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5453. Min Act: -0.0000

Data Index: 868021 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4751. Min Act: -0.0000

Data Index: 189265 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5383. Min Act: -0.0000

Data Index: 1041844 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4564. Min Act: -0.0000

Data Index: 403483 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4298. Min Act: -0.0001

Data Index: 216755 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4171. Min Act: -0.0001

Data Index: 587840 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.3901. Min Act: -0.0000

Data Index: 121459 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4202. Min Act: -0.0000

Data Index: 778349 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.3306. Min Act: -0.0000

Data Index: 53261 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.3760. Min Act: -0.0000

Data Index: 643047 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.3166. Min Act: -0.0000

Data Index: 641930 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.3058. Min Act: -0.0001

Data Index: 570231 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.2468. Min Act: -0.0000

Data Index: 990623 (C4 (Web Text))

Max Activating Token Index: 187