Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3639 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1330. Min Act: -0.0000

Data Index: 609299 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1225. Min Act: -0.0000

Data Index: 799618 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1337541 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1146. Min Act: -0.0000

Data Index: 23450 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1243012 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1150. Min Act: -0.0000

Data Index: 384227 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1163. Min Act: -0.0000

Data Index: 120858 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1031209 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1066. Min Act: -0.0000

Data Index: 311895 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1068. Min Act: -0.0000

Data Index: 596354 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1084. Min Act: -0.0000

Data Index: 596323 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1039. Min Act: -0.0000

Data Index: 334914 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1040. Min Act: -0.0000

Data Index: 396218 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1073. Min Act: -0.0000

Data Index: 899790 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1105. Min Act: -0.0000

Data Index: 719980 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1055. Min Act: -0.0000

Data Index: 643905 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1181414 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1028532 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1150459 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1076. Min Act: -0.0000

Data Index: 963498 (C4 (Web Text))

Max Activating Token Index: 387