Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2696 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0004

Data Index: 34216 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0167. Min Act: -0.0004

Data Index: 703792 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0174. Min Act: -0.0004

Data Index: 609185 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0163. Min Act: -0.0004

Data Index: 470226 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0157. Min Act: -0.0004

Data Index: 1329823 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0153. Min Act: -0.0004

Data Index: 1035185 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0142. Min Act: -0.0004

Data Index: 1268540 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0141. Min Act: -0.0004

Data Index: 270473 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0137. Min Act: -0.0004

Data Index: 158766 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0127. Min Act: -0.0004

Data Index: 604290 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0117. Min Act: -0.0004

Data Index: 326055 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0130. Min Act: -0.0004

Data Index: 377688 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0123. Min Act: -0.0004

Data Index: 753511 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0132. Min Act: -0.0004

Data Index: 235313 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0125. Min Act: -0.0004

Data Index: 475432 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0126. Min Act: -0.0004

Data Index: 699861 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0118. Min Act: -0.0004

Data Index: 411805 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0117. Min Act: -0.0004

Data Index: 1180422 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0116. Min Act: -0.0004

Data Index: 390539 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0115. Min Act: -0.0004

Data Index: 528736 (C4 (Web Text))

Max Activating Token Index: 105