Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 497 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0127. Min Act: -0.0003

Data Index: 217620 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0112. Min Act: -0.0004

Data Index: 352550 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0107. Min Act: -0.0004

Data Index: 568814 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0106. Min Act: -0.0004

Data Index: 100187 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0103. Min Act: -0.0004

Data Index: 1319392 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0105. Min Act: -0.0003

Data Index: 769867 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0104. Min Act: -0.0004

Data Index: 400618 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0104. Min Act: -0.0003

Data Index: 31917 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0101. Min Act: -0.0003

Data Index: 634285 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0103. Min Act: -0.0003

Data Index: 602727 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0103. Min Act: -0.0003

Data Index: 187312 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0103. Min Act: -0.0004

Data Index: 1307777 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0100. Min Act: -0.0003

Data Index: 218016 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0102. Min Act: -0.0003

Data Index: 81282 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0102. Min Act: -0.0003

Data Index: 715772 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0102. Min Act: -0.0003

Data Index: 172884 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0102. Min Act: -0.0004

Data Index: 752688 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0101. Min Act: -0.0004

Data Index: 151778 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0103. Min Act: -0.0004

Data Index: 466788 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0103. Min Act: -0.0004

Data Index: 122625 (C4 (Web Text))

Max Activating Token Index: 389