Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3837 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0003

Data Index: 428615 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0002

Data Index: 637916 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0002

Data Index: 395029 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1097258 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1015535 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0003

Data Index: 769916 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1211426 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0003

Data Index: 947207 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0003

Data Index: 756116 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0116. Min Act: -0.0003

Data Index: 403855 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0116. Min Act: -0.0003

Data Index: 589260 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0002

Data Index: 835837 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1136437 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0003

Data Index: 243898 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0114. Min Act: -0.0003

Data Index: 549278 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0114. Min Act: -0.0003

Data Index: 637295 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1277522 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0002

Data Index: 562268 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0002

Data Index: 188926 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1008138 (C4 (Web Text))

Max Activating Token Index: 604