Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1500 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1642103 (Python Code)

Max Activating Token Index: 629

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0196. Min Act: -0.0004

Data Index: 1656065 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0173. Min Act: -0.0004

Data Index: 1578887 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0156. Min Act: -0.0004

Data Index: 1506237 (Python Code)

Max Activating Token Index: 655

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0157. Min Act: -0.0004

Data Index: 1463053 (Python Code)

Max Activating Token Index: 599

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0151. Min Act: -0.0004

Data Index: 1450209 (Python Code)

Max Activating Token Index: 709

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0153. Min Act: -0.0004

Data Index: 1622045 (Python Code)

Max Activating Token Index: 796

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0153. Min Act: -0.0004

Data Index: 1463569 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0151. Min Act: -0.0004

Data Index: 1378281 (Python Code)

Max Activating Token Index: 386

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0149. Min Act: -0.0004

Data Index: 1637908 (Python Code)

Max Activating Token Index: 945

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0147. Min Act: -0.0004

Data Index: 1453336 (Python Code)

Max Activating Token Index: 187

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1511297 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0143. Min Act: -0.0004

Data Index: 1419919 (Python Code)

Max Activating Token Index: 298

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0140. Min Act: -0.0004

Data Index: 1403531 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0140. Min Act: -0.0004

Data Index: 1636215 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0140. Min Act: -0.0004

Data Index: 1528083 (Python Code)

Max Activating Token Index: 777

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0136. Min Act: -0.0004

Data Index: 1641034 (Python Code)

Max Activating Token Index: 491

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0138. Min Act: -0.0004

Data Index: 1415677 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0136. Min Act: -0.0004

Data Index: 1546702 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0137. Min Act: -0.0004

Data Index: 1539815 (Python Code)

Max Activating Token Index: 533