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

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

Neuron 5040 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: 3.8852. Min Range: -3.8852

Max Act: 3.8852. Min Act: -0.0000

Data Index: 1567456 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.4037. Min Act: 0.0000

Data Index: 1481602 (Python Code)

Max Activating Token Index: 839

Text #2

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.4366. Min Act: -0.0000

Data Index: 118909 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.9606. Min Act: -0.0000

Data Index: 1545609 (Python Code)

Max Activating Token Index: 378

Text #4

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.0324. Min Act: -0.0000

Data Index: 104859 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 3.8852. Min Range: -3.8852

Max Act: 3.0432. Min Act: 0.0001

Data Index: 1533965 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.7227. Min Act: -0.0000

Data Index: 1524883 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.5756. Min Act: -0.0000

Data Index: 696031 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.5960. Min Act: -0.0000

Data Index: 310001 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.5532. Min Act: -0.0000

Data Index: 1378867 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.5152. Min Act: -0.0000

Data Index: 1609937 (Python Code)

Max Activating Token Index: 484

Text #11

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.6331. Min Act: -0.0000

Data Index: 1423738 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.6264. Min Act: -0.0000

Data Index: 1528667 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.6048. Min Act: -0.0000

Data Index: 1421281 (Python Code)

Max Activating Token Index: 445

Text #14

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.6245. Min Act: 0.0000

Data Index: 1499437 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.7298. Min Act: -0.0000

Data Index: 1374092 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.5482. Min Act: -0.0000

Data Index: 1428528 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.5432. Min Act: 0.0000

Data Index: 1649636 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.3869. Min Act: -0.0000

Data Index: 1444317 (Python Code)

Max Activating Token Index: 556

Text #19

Max Range: 3.8852. Min Range: -3.8852

Max Act: 2.5088. Min Act: -0.0000

Data Index: 1364733 (Python Code)

Max Activating Token Index: 171