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

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

Neuron 3875 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0953. Min Act: -0.0002

Data Index: 653837 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1200612 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0834. Min Act: -0.0001

Data Index: 146985 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0764. Min Act: -0.0002

Data Index: 585852 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1248650 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0790. Min Act: -0.0001

Data Index: 907997 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1027029 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0703. Min Act: -0.0001

Data Index: 946680 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0777. Min Act: -0.0001

Data Index: 604355 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0718. Min Act: -0.0001

Data Index: 741925 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1033783 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1082048 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1268074 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0655. Min Act: -0.0001

Data Index: 606871 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0651. Min Act: -0.0001

Data Index: 276306 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0678. Min Act: -0.0002

Data Index: 583435 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0676. Min Act: -0.0001

Data Index: 521739 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0654. Min Act: -0.0002

Data Index: 476046 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1292875 (C4 (Web Text))

Max Activating Token Index: 17