Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2327 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0799. Min Act: -0.0004

Data Index: 1061694 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0710. Min Act: -0.0004

Data Index: 1312635 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0657. Min Act: -0.0004

Data Index: 1111277 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0658. Min Act: -0.0004

Data Index: 213023 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0683. Min Act: -0.0004

Data Index: 841540 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0629. Min Act: -0.0004

Data Index: 534041 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0652. Min Act: -0.0004

Data Index: 415346 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0625. Min Act: -0.0004

Data Index: 498381 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0646. Min Act: -0.0004

Data Index: 442060 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0610. Min Act: -0.0004

Data Index: 760672 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0629. Min Act: -0.0004

Data Index: 956211 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0606. Min Act: -0.0004

Data Index: 247818 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0591. Min Act: -0.0004

Data Index: 798580 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0612. Min Act: -0.0004

Data Index: 1095034 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0607. Min Act: -0.0004

Data Index: 197967 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0603. Min Act: -0.0004

Data Index: 824368 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0626. Min Act: -0.0004

Data Index: 177216 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0578. Min Act: -0.0004

Data Index: 320153 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0616. Min Act: -0.0004

Data Index: 205643 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0607. Min Act: -0.0004

Data Index: 933899 (C4 (Web Text))

Max Activating Token Index: 230