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

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

Neuron 4890 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0161. Min Act: -0.0002

Data Index: 218249 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0162. Min Act: -0.0002

Data Index: 142627 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0162. Min Act: -0.0002

Data Index: 85360 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1099804 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0156. Min Act: -0.0002

Data Index: 528670 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0152. Min Act: -0.0002

Data Index: 23644 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1278307 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1163382 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1232322 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0153. Min Act: -0.0002

Data Index: 662704 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0147. Min Act: -0.0002

Data Index: 879020 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1172829 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0148. Min Act: -0.0002

Data Index: 571999 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0145. Min Act: -0.0002

Data Index: 188917 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0143. Min Act: -0.0002

Data Index: 405490 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0142. Min Act: -0.0002

Data Index: 572623 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0142. Min Act: -0.0002

Data Index: 525239 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1275799 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0144. Min Act: -0.0002

Data Index: 188164 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1217513 (C4 (Web Text))

Max Activating Token Index: 191