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

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

Neuron 81 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: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1243736 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1160797 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1173427 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0006

Data Index: 435338 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0006

Data Index: 901173 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0006

Data Index: 442533 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0115. Min Act: -0.0006

Data Index: 244423 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0006

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1123746 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1000402 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0115. Min Act: -0.0006

Data Index: 342821 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0114. Min Act: -0.0006

Data Index: 120351 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0115. Min Act: -0.0006

Data Index: 273676 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0006

Data Index: 431808 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1291879 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0113. Min Act: -0.0006

Data Index: 403435 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0006

Data Index: 619427 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0114. Min Act: -0.0006

Data Index: 702800 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0112. Min Act: -0.0006

Data Index: 917133 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0112. Min Act: -0.0006

Data Index: 794272 (C4 (Web Text))

Max Activating Token Index: 52