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

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

Neuron 752 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0138. Min Act: -0.0006

Data Index: 885624 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0006

Data Index: 244926 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0135. Min Act: -0.0007

Data Index: 173392 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1230887 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1074966 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1289039 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1128338 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0006

Data Index: 691941 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1021509 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1104530 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1065583 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0121. Min Act: -0.0006

Data Index: 191368 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0121. Min Act: -0.0006

Data Index: 219433 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0118. Min Act: -0.0006

Data Index: 646660 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0006

Data Index: 600764 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0118. Min Act: -0.0006

Data Index: 216634 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0117. Min Act: -0.0007

Data Index: 830036 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0114. Min Act: -0.0006

Data Index: 556444 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0116. Min Act: -0.0006

Data Index: 184450 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1150625 (C4 (Web Text))

Max Activating Token Index: 299