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

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

Neuron 3102 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: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0003

Data Index: 455986 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1277947 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1061213 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0121. Min Act: -0.0003

Data Index: 507721 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0119. Min Act: -0.0003

Data Index: 241465 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0117. Min Act: -0.0003

Data Index: 765991 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0116. Min Act: -0.0003

Data Index: 443322 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0114. Min Act: -0.0003

Data Index: 684520 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0114. Min Act: -0.0003

Data Index: 2418 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0113. Min Act: -0.0003

Data Index: 504541 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0111. Min Act: -0.0003

Data Index: 867252 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0110. Min Act: -0.0003

Data Index: 596980 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0110. Min Act: -0.0003

Data Index: 947178 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0109. Min Act: -0.0003

Data Index: 919912 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0109. Min Act: -0.0003

Data Index: 575841 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0107. Min Act: -0.0003

Data Index: 722265 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0109. Min Act: -0.0003

Data Index: 353697 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0108. Min Act: -0.0003

Data Index: 102863 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1137421 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0108. Min Act: -0.0002

Data Index: 794322 (C4 (Web Text))

Max Activating Token Index: 208