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

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

Neuron 1408 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0006

Data Index: 388532 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0006

Data Index: 457599 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0006

Data Index: 55430 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1313014 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0006

Data Index: 286578 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0006

Data Index: 141547 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0006

Data Index: 536539 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0114. Min Act: -0.0006

Data Index: 55540 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0006

Data Index: 678733 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0006

Data Index: 247053 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0108. Min Act: -0.0006

Data Index: 877783 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1210988 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1132855 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1106342 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1254055 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1157047 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1311890 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0108. Min Act: -0.0006

Data Index: 452518 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0107. Min Act: -0.0006

Data Index: 475285 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0105. Min Act: -0.0006

Data Index: 734448 (C4 (Web Text))

Max Activating Token Index: 42