Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4073 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1021. Min Range: -1.1021

Max Act: 1.0658. Min Act: -0.0000

Data Index: 996497 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.1021. Min Range: -1.1021

Max Act: 1.1021. Min Act: -0.0000

Data Index: 440172 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 1.1021. Min Range: -1.1021

Max Act: 1.0495. Min Act: -0.0000

Data Index: 151384 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 1.1021. Min Range: -1.1021

Max Act: 1.0285. Min Act: -0.0000

Data Index: 716035 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.9768. Min Act: -0.0000

Data Index: 306523 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 1.1021. Min Range: -1.1021

Max Act: 1.0091. Min Act: -0.0000

Data Index: 584198 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.9767. Min Act: -0.0000

Data Index: 620132 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.1021. Min Range: -1.1021

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1169836 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1159565 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.8943. Min Act: -0.0000

Data Index: 871724 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.9766. Min Act: -0.0000

Data Index: 394132 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.9485. Min Act: -0.0000

Data Index: 577203 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.8928. Min Act: -0.0000

Data Index: 249295 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.9563. Min Act: -0.0000

Data Index: 737283 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.9189. Min Act: -0.0000

Data Index: 403048 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1195979 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1284253 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.7848. Min Act: -0.0000

Data Index: 28671 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.9022. Min Act: -0.0000

Data Index: 172233 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.1021. Min Range: -1.1021

Max Act: 0.8924. Min Act: -0.0000

Data Index: 595728 (C4 (Web Text))

Max Activating Token Index: 470