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

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

Neuron 582 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: 0.1361. Min Range: -0.1361

Max Act: 0.1361. Min Act: -0.0002

Data Index: 1311009 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1239. Min Act: -0.0002

Data Index: 967802 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1321. Min Act: -0.0002

Data Index: 303939 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1251. Min Act: -0.0001

Data Index: 91559 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1108330 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1268. Min Act: -0.0002

Data Index: 294090 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1219. Min Act: -0.0001

Data Index: 607983 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1161746 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1205. Min Act: -0.0001

Data Index: 890180 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1145761 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1277440 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1276279 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1219. Min Act: -0.0002

Data Index: 728600 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1150. Min Act: -0.0002

Data Index: 723666 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1311547 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1153. Min Act: -0.0002

Data Index: 600810 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1135. Min Act: -0.0002

Data Index: 377172 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1118. Min Act: -0.0002

Data Index: 419161 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1107. Min Act: -0.0000

Data Index: 470327 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1085. Min Act: -0.0001

Data Index: 298695 (C4 (Web Text))

Max Activating Token Index: 626