Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2182 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.8883. Min Act: -0.0003

Data Index: 1614889 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.8541. Min Act: -0.0003

Data Index: 1604252 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.8224. Min Act: -0.0003

Data Index: 1442044 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.8006. Min Act: -0.0003

Data Index: 1585415 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.8316. Min Act: -0.0003

Data Index: 1594344 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7941. Min Act: -0.0003

Data Index: 1468785 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7675. Min Act: -0.0003

Data Index: 1412540 (Python Code)

Max Activating Token Index: 386

Text #7

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.8157. Min Act: -0.0003

Data Index: 1382281 (Python Code)

Max Activating Token Index: 71

Text #8

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7557. Min Act: -0.0003

Data Index: 1544676 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7275. Min Act: -0.0003

Data Index: 1532559 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7853. Min Act: -0.0003

Data Index: 1627823 (Python Code)

Max Activating Token Index: 81

Text #11

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6862. Min Act: -0.0003

Data Index: 1653721 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7778. Min Act: -0.0004

Data Index: 1399213 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7215. Min Act: -0.0003

Data Index: 1469291 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7147. Min Act: -0.0003

Data Index: 1551122 (Python Code)

Max Activating Token Index: 894

Text #15

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7158. Min Act: -0.0003

Data Index: 1577881 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7819. Min Act: -0.0003

Data Index: 1514811 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7376. Min Act: -0.0003

Data Index: 1474834 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7366. Min Act: -0.0003

Data Index: 1464071 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6645. Min Act: -0.0003

Data Index: 1573222 (Python Code)

Max Activating Token Index: 395