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

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

Neuron 2410 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.8833. Min Act: -0.0000

Data Index: 1644394 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.8767. Min Act: -0.0000

Data Index: 1473110 (Python Code)

Max Activating Token Index: 547

Text #2

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.7427. Min Act: -0.0000

Data Index: 1472668 (Python Code)

Max Activating Token Index: 635

Text #3

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.6998. Min Act: -0.0000

Data Index: 1472451 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.2128. Min Act: -0.0000

Data Index: 48011 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.0265. Min Act: -0.0000

Data Index: 58904 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.0290. Min Act: -0.0000

Data Index: 1305850 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.1820. Min Act: -0.0000

Data Index: 751766 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.8083. Min Act: -0.0000

Data Index: 1443360 (Python Code)

Max Activating Token Index: 392

Text #9

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.1477. Min Act: -0.0000

Data Index: 62009 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.9354. Min Act: -0.0000

Data Index: 887239 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.7471. Min Act: -0.0000

Data Index: 1230370 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 4.8833. Min Range: -4.8833

Max Act: 4.0943. Min Act: -0.0000

Data Index: 24861 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.9188. Min Act: -0.0000

Data Index: 872618 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.9299. Min Act: -0.0000

Data Index: 1618047 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.8722. Min Act: -0.0000

Data Index: 861304 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.5429. Min Act: -0.0000

Data Index: 1435622 (Python Code)

Max Activating Token Index: 67

Text #17

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.9538. Min Act: -0.0000

Data Index: 1241912 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.7850. Min Act: -0.0000

Data Index: 1579539 (Python Code)

Max Activating Token Index: 440

Text #19

Max Range: 4.8833. Min Range: -4.8833

Max Act: 3.7890. Min Act: -0.0000

Data Index: 272400 (C4 (Web Text))

Max Activating Token Index: 736