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

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

Neuron 656 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0490. Min Act: -0.0006

Data Index: 783582 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0480. Min Act: -0.0006

Data Index: 1344784 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0496. Min Act: -0.0006

Data Index: 868989 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0483. Min Act: -0.0006

Data Index: 496838 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0488. Min Act: -0.0006

Data Index: 1225988 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0481. Min Act: -0.0006

Data Index: 189433 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0473. Min Act: -0.0006

Data Index: 468433 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0473. Min Act: -0.0006

Data Index: 57853 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0460. Min Act: -0.0006

Data Index: 1296752 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0454. Min Act: -0.0006

Data Index: 995549 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0447. Min Act: -0.0006

Data Index: 567243 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0441. Min Act: -0.0006

Data Index: 200676 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0445. Min Act: -0.0006

Data Index: 871889 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0450. Min Act: -0.0006

Data Index: 528136 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1134815 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0439. Min Act: -0.0006

Data Index: 1046820 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0421. Min Act: -0.0006

Data Index: 632420 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0464. Min Act: -0.0006

Data Index: 1218196 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0424. Min Act: -0.0006

Data Index: 915835 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0451. Min Act: -0.0006

Data Index: 737257 (C4 (Web Text))

Max Activating Token Index: 433