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

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

Neuron 1511 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: 0.0190. Min Range: -0.0190

Max Act: 0.0190. Min Act: -0.0003

Data Index: 507018 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0157. Min Act: -0.0003

Data Index: 375452 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0149. Min Act: -0.0003

Data Index: 736193 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1349528 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1231207 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0123. Min Act: -0.0003

Data Index: 504573 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1056093 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0122. Min Act: -0.0002

Data Index: 533943 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1068751 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0121. Min Act: -0.0003

Data Index: 574324 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0123. Min Act: -0.0003

Data Index: 637121 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0118. Min Act: -0.0003

Data Index: 75044 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0118. Min Act: -0.0003

Data Index: 849641 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0121. Min Act: -0.0003

Data Index: 340907 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0119. Min Act: -0.0003

Data Index: 309198 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0110. Min Act: -0.0003

Data Index: 842407 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1197923 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0117. Min Act: -0.0003

Data Index: 58423 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0111. Min Act: -0.0003

Data Index: 205484 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0110. Min Act: -0.0002

Data Index: 228120 (C4 (Web Text))

Max Activating Token Index: 225