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

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

Neuron 5476 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: 0.1218. Min Range: -0.1218

Max Act: 0.1218. Min Act: -0.0002

Data Index: 624807 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1030. Min Act: -0.0001

Data Index: 653194 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0951. Min Act: -0.0002

Data Index: 375777 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0920. Min Act: -0.0001

Data Index: 308780 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0992. Min Act: -0.0001

Data Index: 272046 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0868. Min Act: -0.0001

Data Index: 489881 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0932. Min Act: -0.0001

Data Index: 186791 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0934. Min Act: -0.0001

Data Index: 765342 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0979. Min Act: -0.0001

Data Index: 896409 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0902. Min Act: -0.0001

Data Index: 908654 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1056894 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0888. Min Act: -0.0001

Data Index: 232884 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1204062 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1010335 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0877. Min Act: -0.0001

Data Index: 240755 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0870. Min Act: -0.0001

Data Index: 383754 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1122571 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0836. Min Act: -0.0001

Data Index: 497975 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0888. Min Act: -0.0001

Data Index: 441456 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0827. Min Act: -0.0001

Data Index: 714419 (C4 (Web Text))

Max Activating Token Index: 27