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

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

Neuron 2096 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1143. Min Act: -0.0000

Data Index: 609871 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0992. Min Act: -0.0000

Data Index: 936095 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0927. Min Act: -0.0000

Data Index: 704730 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0947. Min Act: -0.0000

Data Index: 790137 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0904. Min Act: -0.0000

Data Index: 861974 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1297172 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0803. Min Act: -0.0000

Data Index: 115040 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0838. Min Act: -0.0000

Data Index: 590031 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1242958 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0819. Min Act: -0.0000

Data Index: 396388 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0845. Min Act: -0.0000

Data Index: 460941 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0804. Min Act: -0.0000

Data Index: 283690 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0828. Min Act: -0.0000

Data Index: 38969 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0827. Min Act: -0.0000

Data Index: 960607 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0824. Min Act: -0.0000

Data Index: 72826 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0791. Min Act: -0.0000

Data Index: 973695 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0813. Min Act: -0.0000

Data Index: 481432 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0842. Min Act: -0.0000

Data Index: 901259 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1094936 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1114007 (C4 (Web Text))

Max Activating Token Index: 632