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

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

Neuron 5162 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: 2.8401. Min Range: -2.8401

Max Act: 2.8401. Min Act: -0.0000

Data Index: 1429932 (Python Code)

Max Activating Token Index: 485

Text #1

Max Range: 2.8401. Min Range: -2.8401

Max Act: 2.5466. Min Act: -0.0000

Data Index: 1459458 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 2.8401. Min Range: -2.8401

Max Act: 2.3948. Min Act: -0.0000

Data Index: 774416 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 2.8401. Min Range: -2.8401

Max Act: 2.2860. Min Act: -0.0000

Data Index: 511544 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 2.8401. Min Range: -2.8401

Max Act: 2.5667. Min Act: -0.0000

Data Index: 1645903 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.8472. Min Act: -0.0000

Data Index: 1610571 (Python Code)

Max Activating Token Index: 249

Text #6

Max Range: 2.8401. Min Range: -2.8401

Max Act: 2.1508. Min Act: -0.0000

Data Index: 1643274 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 2.8401. Min Range: -2.8401

Max Act: 2.0376. Min Act: -0.0000

Data Index: 1444606 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.7556. Min Act: -0.0001

Data Index: 277128 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.8098. Min Act: -0.0000

Data Index: 1611900 (Python Code)

Max Activating Token Index: 621

Text #10

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.9496. Min Act: -0.0000

Data Index: 1525131 (Python Code)

Max Activating Token Index: 606

Text #11

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.8362. Min Act: -0.0000

Data Index: 1481671 (Python Code)

Max Activating Token Index: 793

Text #12

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.6870. Min Act: -0.0000

Data Index: 1496049 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 2.8401. Min Range: -2.8401

Max Act: 2.1032. Min Act: -0.0000

Data Index: 1477765 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.7592. Min Act: -0.0000

Data Index: 1523275 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.7756. Min Act: -0.0000

Data Index: 1500698 (Python Code)

Max Activating Token Index: 511

Text #16

Max Range: 2.8401. Min Range: -2.8401

Max Act: 2.0753. Min Act: -0.0000

Data Index: 1558338 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.7670. Min Act: -0.0000

Data Index: 1567366 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.6652. Min Act: -0.0000

Data Index: 1540260 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 2.8401. Min Range: -2.8401

Max Act: 1.6495. Min Act: -0.0000

Data Index: 1624454 (Python Code)

Max Activating Token Index: 195