Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1884 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0001

Data Index: 419924 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0133. Min Act: -0.0002

Data Index: 521513 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1195685 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0122. Min Act: -0.0002

Data Index: 918233 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0120. Min Act: -0.0001

Data Index: 1554337 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0126. Min Act: -0.0002

Data Index: 280345 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1368901 (Python Code)

Max Activating Token Index: 60

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1502482 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1353896 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0114. Min Act: -0.0002

Data Index: 587820 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0119. Min Act: -0.0002

Data Index: 314055 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0120. Min Act: -0.0002

Data Index: 489962 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0116. Min Act: -0.0002

Data Index: 118555 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1241008 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1238426 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0118. Min Act: -0.0001

Data Index: 561539 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0120. Min Act: -0.0002

Data Index: 731022 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1185528 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0117. Min Act: -0.0001

Data Index: 1606693 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1198584 (C4 (Web Text))

Max Activating Token Index: 454