Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2730 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.8724. Min Act: -0.0000

Data Index: 49771 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 3.0581. Min Range: -3.0581

Max Act: 3.0581. Min Act: -0.0000

Data Index: 138528 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.8348. Min Act: -0.0000

Data Index: 1077475 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.6902. Min Act: -0.0000

Data Index: 708264 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.5516. Min Act: -0.0000

Data Index: 1015591 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.3924. Min Act: -0.0000

Data Index: 1305711 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.3790. Min Act: -0.0000

Data Index: 44467 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.2429. Min Act: -0.0000

Data Index: 1055741 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.2392. Min Act: -0.0000

Data Index: 424346 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.2886. Min Act: -0.0000

Data Index: 690620 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.2710. Min Act: -0.0000

Data Index: 853097 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.2434. Min Act: -0.0000

Data Index: 92904 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.1539. Min Act: -0.0000

Data Index: 374455 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.2219. Min Act: -0.0000

Data Index: 272104 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.2986. Min Act: -0.0000

Data Index: 722441 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.1382. Min Act: -0.0000

Data Index: 390145 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.2425. Min Act: -0.0000

Data Index: 1321387 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.0512. Min Act: -0.0000

Data Index: 1480899 (Python Code)

Max Activating Token Index: 237

Text #18

Max Range: 3.0581. Min Range: -3.0581

Max Act: 2.1356. Min Act: -0.0000

Data Index: 205180 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 3.0581. Min Range: -3.0581

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1388468 (Python Code)

Max Activating Token Index: 281