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

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

Neuron 4643 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0122. Min Act: -0.0002

Data Index: 170969 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0120. Min Act: -0.0002

Data Index: 424645 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1338277 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0103. Min Act: -0.0002

Data Index: 316901 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0109. Min Act: -0.0002

Data Index: 657648 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0113. Min Act: -0.0002

Data Index: 443722 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0107. Min Act: -0.0002

Data Index: 436517 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1223650 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0097. Min Act: -0.0002

Data Index: 485598 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0081. Min Act: -0.0002

Data Index: 1405868 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1024991 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0084. Min Act: -0.0002

Data Index: 639237 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1091013 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0092. Min Act: -0.0002

Data Index: 526051 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0081. Min Act: -0.0002

Data Index: 1650405 (Python Code)

Max Activating Token Index: 396

Text #15

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1075518 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0082. Min Act: -0.0002

Data Index: 418963 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0085. Min Act: -0.0002

Data Index: 891208 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0085. Min Act: -0.0002

Data Index: 943378 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0080. Min Act: -0.0002

Data Index: 897739 (C4 (Web Text))

Max Activating Token Index: 264