Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0123. Min Act: -0.0006

Data Index: 993587 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0121. Min Act: -0.0006

Data Index: 429363 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0120. Min Act: -0.0006

Data Index: 154848 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1015547 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1176872 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0117. Min Act: -0.0006

Data Index: 630888 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0113. Min Act: -0.0006

Data Index: 481915 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0115. Min Act: -0.0006

Data Index: 447504 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0115. Min Act: -0.0006

Data Index: 745285 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0111. Min Act: -0.0006

Data Index: 309187 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0110. Min Act: -0.0006

Data Index: 729831 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0111. Min Act: -0.0006

Data Index: 190325 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0108. Min Act: -0.0006

Data Index: 329134 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0112. Min Act: -0.0006

Data Index: 828230 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0006

Data Index: 749022 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0107. Min Act: -0.0006

Data Index: 351002 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1229402 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1083605 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0095. Min Act: -0.0006

Data Index: 826348 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1223070 (C4 (Web Text))

Max Activating Token Index: 119