Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 509 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1513641 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0112. Min Act: -0.0006

Data Index: 364311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1271422 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0108. Min Act: -0.0006

Data Index: 22029 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0107. Min Act: -0.0006

Data Index: 441720 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0106. Min Act: -0.0006

Data Index: 179093 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0109. Min Act: -0.0006

Data Index: 56771 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1220910 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0106. Min Act: -0.0007

Data Index: 384603 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0105. Min Act: -0.0006

Data Index: 32057 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0105. Min Act: -0.0006

Data Index: 248507 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1084970 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0105. Min Act: -0.0006

Data Index: 741039 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0104. Min Act: -0.0006

Data Index: 895485 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0106. Min Act: -0.0006

Data Index: 517062 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0101. Min Act: -0.0007

Data Index: 147595 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1000669 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0102. Min Act: -0.0005

Data Index: 203033 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0104. Min Act: -0.0006

Data Index: 156306 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0102. Min Act: -0.0005

Data Index: 1450645 (Python Code)

Max Activating Token Index: 1023