Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1725 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1388406 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1368412 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1422976 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1430766 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1587627 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1390419 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1507997 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1374012 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1632147 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0132. Min Act: -0.0005

Data Index: 1407489 (Python Code)

Max Activating Token Index: 595

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1433119 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1614879 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1515626 (Python Code)

Max Activating Token Index: 161

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1437319 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1623938 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1620903 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1640223 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1497606 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1621125 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1382997 (Python Code)

Max Activating Token Index: 970