Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 186 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1155263 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0648. Min Act: -0.0002

Data Index: 836221 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0657. Min Act: -0.0002

Data Index: 815021 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0677. Min Act: -0.0002

Data Index: 231864 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1047784 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1536906 (Python Code)

Max Activating Token Index: 682

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0589. Min Act: -0.0002

Data Index: 534217 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0616. Min Act: -0.0002

Data Index: 739509 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1001356 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1337049 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1351114 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1180158 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1166627 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1424028 (Python Code)

Max Activating Token Index: 485

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1475078 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0583. Min Act: -0.0002

Data Index: 157054 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0587. Min Act: -0.0002

Data Index: 97176 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1477833 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0572. Min Act: -0.0002

Data Index: 303321 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0582. Min Act: -0.0002

Data Index: 960777 (C4 (Web Text))

Max Activating Token Index: 183