Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3266 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0945. Min Act: -0.0000

Data Index: 450950 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0837. Min Act: -0.0001

Data Index: 751266 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0796. Min Act: -0.0001

Data Index: 490896 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1297569 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0808. Min Act: -0.0001

Data Index: 573390 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1043412 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0708. Min Act: -0.0001

Data Index: 748875 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0694. Min Act: -0.0001

Data Index: 280566 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0662. Min Act: -0.0001

Data Index: 850642 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0658. Min Act: -0.0001

Data Index: 277227 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0675. Min Act: -0.0000

Data Index: 728514 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1240733 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0650. Min Act: -0.0000

Data Index: 15541 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0645. Min Act: -0.0001

Data Index: 635251 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0646. Min Act: -0.0000

Data Index: 91252 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0661. Min Act: -0.0001

Data Index: 864240 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1280162 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1336299 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0652. Min Act: -0.0001

Data Index: 491359 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1245838 (C4 (Web Text))

Max Activating Token Index: 956