Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 390 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0127. Min Act: -0.0006

Data Index: 376163 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0124. Min Act: -0.0006

Data Index: 732578 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1025483 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0119. Min Act: -0.0006

Data Index: 919943 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0120. Min Act: -0.0006

Data Index: 83013 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1166320 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0120. Min Act: -0.0006

Data Index: 4784 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1265556 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0117. Min Act: -0.0006

Data Index: 413127 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0117. Min Act: -0.0006

Data Index: 943469 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1349814 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1622872 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1139532 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0114. Min Act: -0.0006

Data Index: 582211 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0110. Min Act: -0.0006

Data Index: 75689 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0110. Min Act: -0.0006

Data Index: 950545 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0110. Min Act: -0.0006

Data Index: 152223 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0112. Min Act: -0.0006

Data Index: 362323 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1244576 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1555230 (Python Code)

Max Activating Token Index: 485