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

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

Neuron 992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0142. Min Act: -0.0003

Data Index: 870951 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0140. Min Act: -0.0003

Data Index: 720570 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0124. Min Act: -0.0003

Data Index: 703703 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0132. Min Act: -0.0003

Data Index: 485331 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0124. Min Act: -0.0004

Data Index: 774884 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0125. Min Act: -0.0004

Data Index: 165327 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0119. Min Act: -0.0003

Data Index: 617226 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1111090 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0117. Min Act: -0.0003

Data Index: 395321 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0121. Min Act: -0.0003

Data Index: 833255 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0123. Min Act: -0.0003

Data Index: 990254 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1165030 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0121. Min Act: -0.0003

Data Index: 377675 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0131. Min Act: -0.0003

Data Index: 428481 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1258788 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0111. Min Act: -0.0003

Data Index: 654336 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0113. Min Act: -0.0003

Data Index: 1197268 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0115. Min Act: -0.0003

Data Index: 685239 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0112. Min Act: -0.0003

Data Index: 194797 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0111. Min Act: -0.0003

Data Index: 802073 (C4 (Web Text))

Max Activating Token Index: 37