Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1727 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0672. Min Act: -0.0001

Data Index: 71382 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1079038 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1071763 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0648. Min Act: -0.0001

Data Index: 83192 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0662. Min Act: -0.0001

Data Index: 729999 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0633. Min Act: -0.0001

Data Index: 744919 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1303944 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0638. Min Act: -0.0001

Data Index: 239750 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0617. Min Act: -0.0001

Data Index: 514085 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0619. Min Act: -0.0001

Data Index: 154071 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1206315 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0587. Min Act: -0.0001

Data Index: 40905 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0584. Min Act: -0.0001

Data Index: 836812 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1045344 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0603. Min Act: -0.0001

Data Index: 283052 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0603. Min Act: -0.0001

Data Index: 269867 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1203286 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1327619 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1157630 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1010626 (C4 (Web Text))

Max Activating Token Index: 799