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

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

Neuron 1307 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: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0003

Data Index: 520929 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1304327 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0003

Data Index: 467426 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1253772 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1269734 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1147245 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0118. Min Act: -0.0003

Data Index: 21192 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1301744 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0003

Data Index: 355674 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1309800 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0003

Data Index: 534204 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0003

Data Index: 412032 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0003

Data Index: 118018 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1204837 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0003

Data Index: 813954 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1273136 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0003

Data Index: 417976 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0003

Data Index: 658889 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1095656 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0003

Data Index: 552797 (C4 (Web Text))

Max Activating Token Index: 798