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

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

Neuron 44 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: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0004

Data Index: 171007 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0130. Min Act: -0.0004

Data Index: 3039 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0129. Min Act: -0.0003

Data Index: 103808 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1287235 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0003

Data Index: 83625 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0127. Min Act: -0.0003

Data Index: 86151 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0003

Data Index: 453889 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1195041 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1018377 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0004

Data Index: 345234 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1019132 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1141701 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0123. Min Act: -0.0003

Data Index: 134507 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0123. Min Act: -0.0004

Data Index: 762147 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0120. Min Act: -0.0003

Data Index: 385614 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0004

Data Index: 229690 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1311034 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0119. Min Act: -0.0003

Data Index: 111632 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1323935 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0124. Min Act: -0.0003

Data Index: 408831 (C4 (Web Text))

Max Activating Token Index: 1007