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

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

Neuron 2605 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0151. Min Act: -0.0001

Data Index: 295689 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0150. Min Act: -0.0001

Data Index: 405064 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0147. Min Act: -0.0001

Data Index: 627062 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0133. Min Act: -0.0001

Data Index: 1140620 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0132. Min Act: -0.0001

Data Index: 1114600 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0131. Min Act: -0.0001

Data Index: 257225 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0138. Min Act: -0.0001

Data Index: 133958 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0121. Min Act: -0.0001

Data Index: 895636 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0123. Min Act: -0.0001

Data Index: 363501 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0117. Min Act: -0.0001

Data Index: 143484 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0112. Min Act: -0.0001

Data Index: 1088434 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0130. Min Act: -0.0001

Data Index: 915389 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0122. Min Act: -0.0001

Data Index: 10935 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0130. Min Act: -0.0001

Data Index: 138162 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0112. Min Act: -0.0001

Data Index: 1232641 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0119. Min Act: -0.0001

Data Index: 556440 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0118. Min Act: -0.0001

Data Index: 816486 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0113. Min Act: -0.0001

Data Index: 519248 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0114. Min Act: -0.0001

Data Index: 1041397 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0116. Min Act: -0.0001

Data Index: 724889 (C4 (Web Text))

Max Activating Token Index: 977