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

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

Neuron 5508 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0001

Data Index: 782115 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1022. Min Act: -0.0001

Data Index: 974897 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0948. Min Act: -0.0001

Data Index: 510495 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0995. Min Act: -0.0001

Data Index: 546945 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1013. Min Act: -0.0001

Data Index: 981400 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1104434 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0963. Min Act: -0.0001

Data Index: 969380 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0994. Min Act: -0.0001

Data Index: 893812 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0989. Min Act: -0.0001

Data Index: 308270 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0934. Min Act: -0.0001

Data Index: 696015 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0939. Min Act: -0.0001

Data Index: 22016 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1014. Min Act: -0.0001

Data Index: 719082 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1270410 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0900. Min Act: -0.0001

Data Index: 729154 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0891. Min Act: -0.0001

Data Index: 657181 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0873. Min Act: -0.0001

Data Index: 620576 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0816. Min Act: -0.0001

Data Index: 483782 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0848. Min Act: -0.0001

Data Index: 11910 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0868. Min Act: -0.0001

Data Index: 853881 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0885. Min Act: -0.0001

Data Index: 985940 (C4 (Web Text))

Max Activating Token Index: 259