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

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

Neuron 130 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: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1375787 (Python Code)

Max Activating Token Index: 350

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0225. Min Act: -0.0003

Data Index: 193490 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1453101 (Python Code)

Max Activating Token Index: 555

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1509912 (Python Code)

Max Activating Token Index: 566

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1460134 (Python Code)

Max Activating Token Index: 139

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1364900 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0191. Min Act: -0.0003

Data Index: 835307 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1633249 (Python Code)

Max Activating Token Index: 452

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1542154 (Python Code)

Max Activating Token Index: 677

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0184. Min Act: -0.0003

Data Index: 158014 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1439961 (Python Code)

Max Activating Token Index: 967

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1492697 (Python Code)

Max Activating Token Index: 251

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1419186 (Python Code)

Max Activating Token Index: 56

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1494289 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1310887 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1427852 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1490996 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1447692 (Python Code)

Max Activating Token Index: 399

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1634202 (Python Code)

Max Activating Token Index: 744

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1363167 (Python Code)

Max Activating Token Index: 411