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

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

Neuron 536 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: 0.0130. Min Range: -0.0130

Max Act: 0.0130. Min Act: -0.0006

Data Index: 171771 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1192603 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0124. Min Act: -0.0006

Data Index: 98946 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0120. Min Act: -0.0006

Data Index: 360844 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0125. Min Act: -0.0006

Data Index: 886342 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0116. Min Act: -0.0006

Data Index: 728753 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0006

Data Index: 502890 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1217568 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1077857 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0124. Min Act: -0.0006

Data Index: 939187 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0113. Min Act: -0.0006

Data Index: 923551 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0107. Min Act: -0.0006

Data Index: 58747 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0115. Min Act: -0.0006

Data Index: 225246 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0115. Min Act: -0.0006

Data Index: 617194 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0109. Min Act: -0.0006

Data Index: 43053 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1041316 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0106. Min Act: -0.0006

Data Index: 77956 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0117. Min Act: -0.0006

Data Index: 419868 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0122. Min Act: -0.0006

Data Index: 339706 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1142719 (C4 (Web Text))

Max Activating Token Index: 167