Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4699 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0002

Data Index: 737482 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1642380 (Python Code)

Max Activating Token Index: 235

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1553633 (Python Code)

Max Activating Token Index: 814

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1409120 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0128. Min Act: -0.0002

Data Index: 63804 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1463999 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1284319 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1457984 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1532536 (Python Code)

Max Activating Token Index: 319

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0124. Min Act: -0.0002

Data Index: 190458 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0127. Min Act: -0.0002

Data Index: 359941 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0127. Min Act: -0.0002

Data Index: 366449 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1471068 (Python Code)

Max Activating Token Index: 695

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1588502 (Python Code)

Max Activating Token Index: 198

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1579891 (Python Code)

Max Activating Token Index: 567

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1404407 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1525713 (Python Code)

Max Activating Token Index: 780

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1549223 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0123. Min Act: -0.0002

Data Index: 112391 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0123. Min Act: -0.0002

Data Index: 548284 (C4 (Web Text))

Max Activating Token Index: 318