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

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

Neuron 3223 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: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0002

Data Index: 493603 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0726. Min Act: -0.0002

Data Index: 119356 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0695. Min Act: -0.0002

Data Index: 304852 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0673. Min Act: -0.0003

Data Index: 138569 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0672. Min Act: -0.0003

Data Index: 881771 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1305472 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1325070 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0661. Min Act: -0.0002

Data Index: 248018 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0647. Min Act: -0.0003

Data Index: 448467 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0633. Min Act: -0.0003

Data Index: 426181 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0628. Min Act: -0.0003

Data Index: 846663 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0625. Min Act: -0.0003

Data Index: 841078 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0621. Min Act: -0.0003

Data Index: 561584 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0616. Min Act: -0.0003

Data Index: 250632 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0610. Min Act: -0.0003

Data Index: 861996 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0607. Min Act: -0.0003

Data Index: 292297 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0598. Min Act: -0.0003

Data Index: 181012 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0588. Min Act: -0.0002

Data Index: 56010 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1318927 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0596. Min Act: -0.0003

Data Index: 61254 (C4 (Web Text))

Max Activating Token Index: 888