Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4715 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0003

Data Index: 747958 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0763. Min Act: -0.0003

Data Index: 585326 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0776. Min Act: -0.0003

Data Index: 358519 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0713. Min Act: -0.0003

Data Index: 732664 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0724. Min Act: -0.0003

Data Index: 988276 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0719. Min Act: -0.0003

Data Index: 782170 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0707. Min Act: -0.0003

Data Index: 637835 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1343288 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1210384 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0657. Min Act: -0.0003

Data Index: 420877 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0660. Min Act: -0.0002

Data Index: 185486 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0638. Min Act: -0.0003

Data Index: 522532 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0647. Min Act: -0.0003

Data Index: 816752 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0622. Min Act: -0.0003

Data Index: 228999 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0637. Min Act: -0.0002

Data Index: 889502 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1188158 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0649. Min Act: -0.0003

Data Index: 280700 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0613. Min Act: -0.0002

Data Index: 26864 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0629. Min Act: -0.0003

Data Index: 437587 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0627. Min Act: -0.0003

Data Index: 229015 (C4 (Web Text))

Max Activating Token Index: 327