Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1026 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1229. Min Range: -2.1229

Max Act: 2.1229. Min Act: -0.0000

Data Index: 1578056 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.9684. Min Act: -0.0000

Data Index: 1583368 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.9465. Min Act: -0.0000

Data Index: 1370472 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.7308. Min Act: -0.0000

Data Index: 1366611 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.6926. Min Act: -0.0000

Data Index: 1595619 (Python Code)

Max Activating Token Index: 99

Text #5

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.5468. Min Act: -0.0000

Data Index: 1626999 (Python Code)

Max Activating Token Index: 77

Text #6

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.4443. Min Act: -0.0000

Data Index: 1367715 (Python Code)

Max Activating Token Index: 770

Text #7

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1613720 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1591004 (Python Code)

Max Activating Token Index: 345

Text #9

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1626094 (Python Code)

Max Activating Token Index: 778

Text #10

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.2445. Min Act: -0.0000

Data Index: 1605654 (Python Code)

Max Activating Token Index: 887

Text #11

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1475940 (Python Code)

Max Activating Token Index: 170

Text #12

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.4112. Min Act: -0.0000

Data Index: 1373295 (Python Code)

Max Activating Token Index: 784

Text #13

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1565438 (Python Code)

Max Activating Token Index: 889

Text #14

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1490708 (Python Code)

Max Activating Token Index: 527

Text #15

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1568491 (Python Code)

Max Activating Token Index: 592

Text #16

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.8629. Min Act: -0.0000

Data Index: 1551035 (Python Code)

Max Activating Token Index: 855

Text #17

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1567005 (Python Code)

Max Activating Token Index: 923

Text #18

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.3563. Min Act: -0.0000

Data Index: 1509555 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 2.1229. Min Range: -2.1229

Max Act: 1.0280. Min Act: -0.0000

Data Index: 1448280 (Python Code)

Max Activating Token Index: 282