Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1727 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0006

Data Index: 849777 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0144. Min Act: -0.0006

Data Index: 21909 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0136. Min Act: -0.0006

Data Index: 191485 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0124. Min Act: -0.0006

Data Index: 645812 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0129. Min Act: -0.0006

Data Index: 349444 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1105590 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0124. Min Act: -0.0006

Data Index: 437140 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0121. Min Act: -0.0006

Data Index: 552758 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0123. Min Act: -0.0006

Data Index: 563918 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0116. Min Act: -0.0006

Data Index: 195984 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0117. Min Act: -0.0006

Data Index: 361469 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1089874 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0117. Min Act: -0.0006

Data Index: 3719 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1217834 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0111. Min Act: -0.0006

Data Index: 914334 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0113. Min Act: -0.0006

Data Index: 765330 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0118. Min Act: -0.0006

Data Index: 770275 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1161275 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0108. Min Act: -0.0006

Data Index: 107407 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1349831 (C4 (Web Text))

Max Activating Token Index: 411