Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1200 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0151. Min Act: -0.0003

Data Index: 707373 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0138. Min Act: -0.0003

Data Index: 855157 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0145. Min Act: -0.0002

Data Index: 120669 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0133. Min Act: -0.0003

Data Index: 303686 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0124. Min Act: -0.0003

Data Index: 745991 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1155065 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1142609 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0121. Min Act: -0.0003

Data Index: 646988 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0127. Min Act: -0.0003

Data Index: 242300 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0130. Min Act: -0.0003

Data Index: 857 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0124. Min Act: -0.0003

Data Index: 210769 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0119. Min Act: -0.0003

Data Index: 994845 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0117. Min Act: -0.0002

Data Index: 465935 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0112. Min Act: -0.0003

Data Index: 908412 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0118. Min Act: -0.0002

Data Index: 10744 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0120. Min Act: -0.0003

Data Index: 288407 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1292262 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0110. Min Act: -0.0003

Data Index: 141048 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0113. Min Act: -0.0002

Data Index: 245451 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0127. Min Act: -0.0003

Data Index: 678721 (C4 (Web Text))

Max Activating Token Index: 625