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

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

Neuron 5621 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: 0.0000

Data Index: 189196 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0135. Min Act: 0.0000

Data Index: 372693 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0134. Min Act: 0.0000

Data Index: 728384 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0127. Min Act: 0.0000

Data Index: 233536 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0128. Min Act: -0.0000

Data Index: 1456329 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0116. Min Act: -0.0000

Data Index: 530357 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0115. Min Act: 0.0000

Data Index: 1600809 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0118. Min Act: -0.0000

Data Index: 601452 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0120. Min Act: 0.0000

Data Index: 72783 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0115. Min Act: 0.0000

Data Index: 145400 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0114. Min Act: -0.0000

Data Index: 969255 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0111. Min Act: -0.0000

Data Index: 109969 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0111. Min Act: -0.0000

Data Index: 1518316 (Python Code)

Max Activating Token Index: 509

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0110. Min Act: 0.0000

Data Index: 1180636 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0109. Min Act: 0.0000

Data Index: 1428505 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0104. Min Act: 0.0001

Data Index: 1077582 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0105. Min Act: -0.0000

Data Index: 1421771 (Python Code)

Max Activating Token Index: 209

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0109. Min Act: -0.0000

Data Index: 1095211 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0112. Min Act: 0.0000

Data Index: 405625 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0102. Min Act: -0.0000

Data Index: 1564609 (Python Code)

Max Activating Token Index: 1005