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

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

Neuron 3896 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.6252. Min Act: -0.0000

Data Index: 1576870 (Python Code)

Max Activating Token Index: 599

Text #1

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.5218. Min Act: -0.0000

Data Index: 1387713 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.8675. Min Act: -0.0000

Data Index: 1372267 (Python Code)

Max Activating Token Index: 936

Text #3

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.8611. Min Act: -0.0000

Data Index: 1545268 (Python Code)

Max Activating Token Index: 825

Text #4

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.6182. Min Act: -0.0000

Data Index: 1506496 (Python Code)

Max Activating Token Index: 324

Text #5

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.1325. Min Act: -0.0000

Data Index: 1620049 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.2863. Min Act: -0.0000

Data Index: 1454579 (Python Code)

Max Activating Token Index: 876

Text #7

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.2310. Min Act: -0.0000

Data Index: 1528875 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.1962. Min Act: -0.0000

Data Index: 1585780 (Python Code)

Max Activating Token Index: 1009

Text #9

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.3983. Min Act: -0.0000

Data Index: 1439728 (Python Code)

Max Activating Token Index: 878

Text #10

Max Range: 7.8675. Min Range: -7.8675

Max Act: 6.9538. Min Act: -0.0000

Data Index: 1420017 (Python Code)

Max Activating Token Index: 814

Text #11

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.0628. Min Act: -0.0000

Data Index: 1410465 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 7.8675. Min Range: -7.8675

Max Act: 7.0563. Min Act: -0.0000

Data Index: 1606639 (Python Code)

Max Activating Token Index: 861

Text #13

Max Range: 7.8675. Min Range: -7.8675

Max Act: 6.8273. Min Act: -0.0000

Data Index: 1592053 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 7.8675. Min Range: -7.8675

Max Act: 6.1021. Min Act: -0.0000

Data Index: 1545361 (Python Code)

Max Activating Token Index: 188

Text #15

Max Range: 7.8675. Min Range: -7.8675

Max Act: 6.6965. Min Act: -0.0000

Data Index: 1595844 (Python Code)

Max Activating Token Index: 794

Text #16

Max Range: 7.8675. Min Range: -7.8675

Max Act: 6.8700. Min Act: -0.0000

Data Index: 1610352 (Python Code)

Max Activating Token Index: 100

Text #17

Max Range: 7.8675. Min Range: -7.8675

Max Act: 6.8394. Min Act: -0.0000

Data Index: 1468129 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 7.8675. Min Range: -7.8675

Max Act: 6.8333. Min Act: -0.0000

Data Index: 1432446 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 7.8675. Min Range: -7.8675

Max Act: 6.5948. Min Act: -0.0000

Data Index: 1644953 (Python Code)

Max Activating Token Index: 775