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

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

Neuron 3890 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0002

Data Index: 12812 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1298050 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0143. Min Act: -0.0002

Data Index: 557750 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1381116 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0128. Min Act: -0.0002

Data Index: 493390 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1420619 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1481647 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0150. Min Act: -0.0002

Data Index: 694066 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1620886 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1378660 (Python Code)

Max Activating Token Index: 933

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1460700 (Python Code)

Max Activating Token Index: 27

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0128. Min Act: -0.0002

Data Index: 246823 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1562523 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1526702 (Python Code)

Max Activating Token Index: 1018

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0121. Min Act: -0.0002

Data Index: 216115 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0127. Min Act: -0.0002

Data Index: 874075 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1655003 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1490827 (Python Code)

Max Activating Token Index: 75

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1489043 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1633921 (Python Code)

Max Activating Token Index: 930