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

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

Neuron 2826 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.4843. Min Act: -0.0000

Data Index: 1489163 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.5531. Min Act: -0.0001

Data Index: 1625879 (Python Code)

Max Activating Token Index: 423

Text #2

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.1327. Min Act: -0.0000

Data Index: 1508566 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.2545. Min Act: -0.0000

Data Index: 1533719 (Python Code)

Max Activating Token Index: 289

Text #4

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.3320. Min Act: -0.0001

Data Index: 1435271 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.1359. Min Act: -0.0000

Data Index: 1522882 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.0512. Min Act: -0.0001

Data Index: 1368511 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.0378. Min Act: -0.0001

Data Index: 1614832 (Python Code)

Max Activating Token Index: 923

Text #8

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.0390. Min Act: -0.0000

Data Index: 1543801 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 2.5531. Min Range: -2.5531

Max Act: 1.8263. Min Act: -0.0000

Data Index: 1655372 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.0111. Min Act: -0.0000

Data Index: 1509480 (Python Code)

Max Activating Token Index: 150

Text #11

Max Range: 2.5531. Min Range: -2.5531

Max Act: 1.8046. Min Act: -0.0001

Data Index: 1402829 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.0014. Min Act: -0.0000

Data Index: 1455739 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 2.5531. Min Range: -2.5531

Max Act: 2.0846. Min Act: -0.0001

Data Index: 1588910 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 2.5531. Min Range: -2.5531

Max Act: 1.9805. Min Act: -0.0001

Data Index: 1399130 (Python Code)

Max Activating Token Index: 101

Text #15

Max Range: 2.5531. Min Range: -2.5531

Max Act: 1.9709. Min Act: -0.0001

Data Index: 1419732 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 2.5531. Min Range: -2.5531

Max Act: 1.9645. Min Act: -0.0001

Data Index: 1393978 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 2.5531. Min Range: -2.5531

Max Act: 1.7555. Min Act: -0.0001

Data Index: 1417914 (Python Code)

Max Activating Token Index: 651

Text #18

Max Range: 2.5531. Min Range: -2.5531

Max Act: 1.8467. Min Act: -0.0000

Data Index: 1541484 (Python Code)

Max Activating Token Index: 199

Text #19

Max Range: 2.5531. Min Range: -2.5531

Max Act: 1.9336. Min Act: -0.0001

Data Index: 1618290 (Python Code)

Max Activating Token Index: 97