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

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

Neuron 1428 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1511545 (Python Code)

Max Activating Token Index: 278

Text #1

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0130. Min Act: -0.0006

Data Index: 898967 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0129. Min Act: -0.0005

Data Index: 776429 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0128. Min Act: -0.0005

Data Index: 107096 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0121. Min Act: -0.0005

Data Index: 497183 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0119. Min Act: -0.0005

Data Index: 1272118 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0120. Min Act: -0.0005

Data Index: 767920 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1625158 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0117. Min Act: -0.0005

Data Index: 253794 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0115. Min Act: -0.0005

Data Index: 703426 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0116. Min Act: -0.0005

Data Index: 52153 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0113. Min Act: -0.0006

Data Index: 472765 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0115. Min Act: -0.0005

Data Index: 46930 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0113. Min Act: -0.0005

Data Index: 84624 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1300093 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0113. Min Act: -0.0005

Data Index: 34713 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1419386 (Python Code)

Max Activating Token Index: 583

Text #17

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0113. Min Act: -0.0005

Data Index: 158244 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0113. Min Act: -0.0005

Data Index: 32960 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0112. Min Act: -0.0005

Data Index: 807012 (C4 (Web Text))

Max Activating Token Index: 654