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

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

Neuron 244 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: 0.4047. Min Range: -0.4047

Max Act: 0.4047. Min Act: -0.0001

Data Index: 1326829 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3696. Min Act: -0.0002

Data Index: 158495 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3971. Min Act: -0.0001

Data Index: 211254 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3471. Min Act: -0.0001

Data Index: 688585 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3813. Min Act: -0.0001

Data Index: 1262018 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3383. Min Act: -0.0002

Data Index: 1112395 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3756. Min Act: -0.0002

Data Index: 466930 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3887. Min Act: -0.0001

Data Index: 884191 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3765. Min Act: -0.0001

Data Index: 1014848 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3974. Min Act: -0.0002

Data Index: 1211321 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3500. Min Act: -0.0002

Data Index: 363196 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3465. Min Act: -0.0001

Data Index: 625937 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3591. Min Act: -0.0002

Data Index: 491773 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3538. Min Act: -0.0001

Data Index: 462821 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3656. Min Act: -0.0002

Data Index: 1275722 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.2955. Min Act: -0.0002

Data Index: 176592 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3486. Min Act: -0.0001

Data Index: 21060 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3322. Min Act: -0.0001

Data Index: 1048707 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.2940. Min Act: -0.0002

Data Index: 949476 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3216. Min Act: -0.0001

Data Index: 638704 (C4 (Web Text))

Max Activating Token Index: 709