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

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

Neuron 4382 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1053. Min Act: -0.0002

Data Index: 493229 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1026692 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1326965 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0856. Min Act: -0.0002

Data Index: 728242 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0756. Min Act: -0.0002

Data Index: 183698 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1166018 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0700. Min Act: -0.0002

Data Index: 679990 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0719. Min Act: -0.0002

Data Index: 277815 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0676. Min Act: -0.0002

Data Index: 47420 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1320770 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0602. Min Act: -0.0002

Data Index: 830778 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1143599 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0565. Min Act: -0.0002

Data Index: 432453 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0565. Min Act: -0.0002

Data Index: 152244 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0576. Min Act: -0.0002

Data Index: 240080 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1270032 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0569. Min Act: -0.0002

Data Index: 582473 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0547. Min Act: -0.0002

Data Index: 817808 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0584. Min Act: -0.0002

Data Index: 33320 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0562. Min Act: -0.0002

Data Index: 73095 (C4 (Web Text))

Max Activating Token Index: 130