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

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

Neuron 393 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: 0.1563. Min Range: -0.1563

Max Act: 0.1329. Min Act: -0.0002

Data Index: 682620 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1563. Min Act: -0.0002

Data Index: 624076 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1463. Min Act: -0.0002

Data Index: 248846 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1219. Min Act: -0.0002

Data Index: 416800 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1138. Min Act: -0.0001

Data Index: 87545 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1096. Min Act: -0.0002

Data Index: 227905 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1138. Min Act: -0.0002

Data Index: 346488 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1122. Min Act: -0.0002

Data Index: 315855 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1091363 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1127. Min Act: -0.0002

Data Index: 285292 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1118. Min Act: -0.0002

Data Index: 899102 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1133. Min Act: -0.0002

Data Index: 324625 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1111. Min Act: -0.0001

Data Index: 149003 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1081373 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1076. Min Act: -0.0002

Data Index: 356292 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1037. Min Act: -0.0002

Data Index: 414247 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1134. Min Act: -0.0002

Data Index: 871442 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1119386 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1116. Min Act: -0.0002

Data Index: 121381 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1303582 (C4 (Web Text))

Max Activating Token Index: 100