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

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

Neuron 1143 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: 3.2695. Min Range: -3.2695

Max Act: 3.2160. Min Act: -0.0000

Data Index: 528555 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 3.2695. Min Range: -3.2695

Max Act: 3.0924. Min Act: -0.0000

Data Index: 955226 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 3.2695. Min Range: -3.2695

Max Act: 3.2695. Min Act: -0.0000

Data Index: 987097 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.9113. Min Act: -0.0000

Data Index: 412934 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.9699. Min Act: -0.0000

Data Index: 221354 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.9739. Min Act: -0.0000

Data Index: 1350297 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.8496. Min Act: -0.0000

Data Index: 464252 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.9911. Min Act: -0.0000

Data Index: 992917 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.5355. Min Act: -0.0000

Data Index: 980031 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.5849. Min Act: -0.0000

Data Index: 1155496 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.6636. Min Act: -0.0000

Data Index: 639076 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.7533. Min Act: -0.0000

Data Index: 1142241 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.7491. Min Act: -0.0000

Data Index: 552987 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.7490. Min Act: -0.0000

Data Index: 258965 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.5788. Min Act: -0.0000

Data Index: 371417 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.6621. Min Act: -0.0001

Data Index: 13968 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.5125. Min Act: -0.0000

Data Index: 1170098 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.4883. Min Act: -0.0000

Data Index: 1290982 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.4713. Min Act: -0.0000

Data Index: 147542 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 3.2695. Min Range: -3.2695

Max Act: 2.2250. Min Act: -0.0000

Data Index: 870128 (C4 (Web Text))

Max Activating Token Index: 828