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

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

Neuron 5612 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1547. Min Act: -0.0001

Data Index: 772870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1492. Min Act: -0.0001

Data Index: 668614 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1392. Min Act: -0.0001

Data Index: 450145 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1229. Min Act: -0.0001

Data Index: 166492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1179. Min Act: -0.0001

Data Index: 894630 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1181. Min Act: -0.0001

Data Index: 329137 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1328682 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1366503 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1381146 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1420562 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0857. Min Act: -0.0001

Data Index: 807982 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1554893 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1533745 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1400975 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0722. Min Act: -0.0001

Data Index: 342074 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1413459 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0794. Min Act: -0.0001

Data Index: 63425 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1361633 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1593915 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0676. Min Act: -0.0001

Data Index: 801230 (C4 (Web Text))

Max Activating Token Index: 1023