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

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

Neuron 1481 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: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0003

Data Index: 151970 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0121. Min Act: -0.0003

Data Index: 523647 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0117. Min Act: -0.0003

Data Index: 58693 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0118. Min Act: -0.0003

Data Index: 959361 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0118. Min Act: -0.0003

Data Index: 57723 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0003

Data Index: 1166180 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1256433 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0004

Data Index: 1268486 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0003

Data Index: 743222 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1285741 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1111862 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1288281 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0004

Data Index: 1114034 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1000173 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0004

Data Index: 1017439 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1126506 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1439833 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0003

Data Index: 18278 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1458455 (Python Code)

Max Activating Token Index: 188

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0106. Min Act: -0.0004

Data Index: 1358960 (C4 (Web Text))

Max Activating Token Index: 238