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

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

Neuron 5262 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.5737. Min Act: -0.0001

Data Index: 1467706 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.5083. Min Act: -0.0001

Data Index: 1618942 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.4646. Min Act: -0.0001

Data Index: 1394088 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.3860. Min Act: -0.0000

Data Index: 1508630 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.2975. Min Act: -0.0000

Data Index: 1599091 (Python Code)

Max Activating Token Index: 205

Text #5

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.4229. Min Act: -0.0000

Data Index: 1654752 (Python Code)

Max Activating Token Index: 75

Text #6

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.3067. Min Act: -0.0001

Data Index: 1607750 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.2997. Min Act: -0.0001

Data Index: 1460256 (Python Code)

Max Activating Token Index: 363

Text #8

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.2022. Min Act: -0.0000

Data Index: 1460392 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.2820. Min Act: -0.0000

Data Index: 1621878 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.2764. Min Act: -0.0001

Data Index: 1419500 (Python Code)

Max Activating Token Index: 281

Text #11

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.3442. Min Act: -0.0000

Data Index: 1525601 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.3398. Min Act: -0.0000

Data Index: 1375118 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.3239. Min Act: -0.0000

Data Index: 1597944 (Python Code)

Max Activating Token Index: 276

Text #14

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.2227. Min Act: -0.0001

Data Index: 1585256 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.2103. Min Act: -0.0000

Data Index: 1399689 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.0619. Min Act: -0.0000

Data Index: 1530138 (Python Code)

Max Activating Token Index: 175

Text #17

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.1650. Min Act: -0.0000

Data Index: 1375754 (Python Code)

Max Activating Token Index: 95

Text #18

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.2584. Min Act: -0.0001

Data Index: 1365967 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 2.5737. Min Range: -2.5737

Max Act: 2.1540. Min Act: -0.0000

Data Index: 1386841 (Python Code)

Max Activating Token Index: 172