Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 430 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1406521 (Python Code)

Max Activating Token Index: 320

Text #1

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1395497 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1534403 (Python Code)

Max Activating Token Index: 260

Text #3

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1557186 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1654376 (Python Code)

Max Activating Token Index: 413

Text #5

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1505477 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1412643 (Python Code)

Max Activating Token Index: 836

Text #7

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1458149 (Python Code)

Max Activating Token Index: 526

Text #8

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1484748 (Python Code)

Max Activating Token Index: 646

Text #9

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1499427 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1446893 (Python Code)

Max Activating Token Index: 424

Text #11

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1454959 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1475503 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1628465 (Python Code)

Max Activating Token Index: 374

Text #14

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1390467 (Python Code)

Max Activating Token Index: 266

Text #15

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1408557 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1482745 (Python Code)

Max Activating Token Index: 351

Text #17

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1472406 (Python Code)

Max Activating Token Index: 636

Text #18

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1496399 (Python Code)

Max Activating Token Index: 952

Text #19

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1576233 (Python Code)

Max Activating Token Index: 81