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

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

Neuron 1769 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1337. Min Act: -0.0001

Data Index: 563636 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1275. Min Act: -0.0001

Data Index: 132992 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1222. Min Act: -0.0002

Data Index: 752637 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1243. Min Act: -0.0002

Data Index: 85847 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1192. Min Act: -0.0002

Data Index: 365333 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1219. Min Act: -0.0002

Data Index: 389765 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1115. Min Act: -0.0001

Data Index: 937541 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1094348 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1167. Min Act: -0.0001

Data Index: 900351 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1148. Min Act: -0.0002

Data Index: 214474 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1118. Min Act: -0.0001

Data Index: 994592 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1088. Min Act: -0.0001

Data Index: 748448 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1271195 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1105. Min Act: -0.0002

Data Index: 244492 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1092. Min Act: -0.0002

Data Index: 301404 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1283219 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1330471 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1119. Min Act: -0.0001

Data Index: 536991 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1107. Min Act: -0.0002

Data Index: 932527 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1118. Min Act: -0.0002

Data Index: 134464 (C4 (Web Text))

Max Activating Token Index: 279