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

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

Neuron 3762 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0696. Min Act: -0.0001

Data Index: 1375214 (Python Code)

Max Activating Token Index: 948

Text #1

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.1053. Min Act: -0.0001

Data Index: 1384923 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0873. Min Act: -0.0001

Data Index: 1612122 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0978. Min Act: -0.0001

Data Index: 1568537 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 1.1053. Min Range: -1.1053

Max Act: 0.9765. Min Act: -0.0001

Data Index: 1626447 (Python Code)

Max Activating Token Index: 763

Text #5

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0301. Min Act: -0.0001

Data Index: 1363636 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0268. Min Act: -0.0001

Data Index: 1507405 (Python Code)

Max Activating Token Index: 374

Text #7

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0243. Min Act: -0.0001

Data Index: 1445027 (Python Code)

Max Activating Token Index: 1016

Text #8

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0924. Min Act: -0.0001

Data Index: 1642656 (Python Code)

Max Activating Token Index: 422

Text #9

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0578. Min Act: -0.0001

Data Index: 1624277 (Python Code)

Max Activating Token Index: 625

Text #10

Max Range: 1.1053. Min Range: -1.1053

Max Act: 0.9389. Min Act: -0.0001

Data Index: 1637746 (Python Code)

Max Activating Token Index: 764

Text #11

Max Range: 1.1053. Min Range: -1.1053

Max Act: 0.9998. Min Act: -0.0001

Data Index: 1521158 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.1040. Min Act: -0.0001

Data Index: 1625825 (Python Code)

Max Activating Token Index: 927

Text #13

Max Range: 1.1053. Min Range: -1.1053

Max Act: 0.9394. Min Act: -0.0001

Data Index: 1426829 (Python Code)

Max Activating Token Index: 822

Text #14

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0560. Min Act: -0.0001

Data Index: 1372296 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 1.1053. Min Range: -1.1053

Max Act: 0.9946. Min Act: -0.0001

Data Index: 1396428 (Python Code)

Max Activating Token Index: 987

Text #16

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0655. Min Act: -0.0001

Data Index: 1490367 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 1.1053. Min Range: -1.1053

Max Act: 0.9784. Min Act: -0.0001

Data Index: 1396209 (Python Code)

Max Activating Token Index: 552

Text #18

Max Range: 1.1053. Min Range: -1.1053

Max Act: 1.0055. Min Act: -0.0001

Data Index: 1632847 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 1.1053. Min Range: -1.1053

Max Act: 0.8230. Min Act: -0.0001

Data Index: 1528102 (Python Code)

Max Activating Token Index: 768