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

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

Neuron 3646 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1340351 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0002

Data Index: 869260 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0122. Min Act: -0.0002

Data Index: 482551 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0122. Min Act: -0.0003

Data Index: 524018 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0119. Min Act: -0.0003

Data Index: 375327 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0122. Min Act: -0.0003

Data Index: 682442 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0118. Min Act: -0.0002

Data Index: 209113 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0119. Min Act: -0.0003

Data Index: 797455 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0117. Min Act: -0.0003

Data Index: 301325 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0116. Min Act: -0.0002

Data Index: 459995 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1117062 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0003

Data Index: 873884 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 251407 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0003

Data Index: 278012 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0003

Data Index: 137638 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0003

Data Index: 235603 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0003

Data Index: 605602 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0002

Data Index: 257236 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0110. Min Act: -0.0003

Data Index: 1088702 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0110. Min Act: -0.0002

Data Index: 972879 (C4 (Web Text))

Max Activating Token Index: 939