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

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

Neuron 542 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: 0.1369. Min Range: -0.1369

Max Act: 0.1369. Min Act: -0.0003

Data Index: 1439270 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1375468 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1201. Min Act: -0.0003

Data Index: 1612647 (Python Code)

Max Activating Token Index: 530

Text #3

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1186. Min Act: -0.0002

Data Index: 1495915 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1208. Min Act: -0.0003

Data Index: 1414376 (Python Code)

Max Activating Token Index: 282

Text #5

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1121. Min Act: -0.0003

Data Index: 1586468 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1624486 (Python Code)

Max Activating Token Index: 390

Text #7

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1151. Min Act: -0.0003

Data Index: 1420498 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1125. Min Act: -0.0003

Data Index: 1431423 (Python Code)

Max Activating Token Index: 304

Text #9

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1109. Min Act: -0.0003

Data Index: 1557290 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1142. Min Act: -0.0003

Data Index: 1586900 (Python Code)

Max Activating Token Index: 229

Text #11

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1167. Min Act: -0.0003

Data Index: 1581254 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1132. Min Act: -0.0003

Data Index: 1461119 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1080. Min Act: -0.0003

Data Index: 1502626 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1109. Min Act: -0.0003

Data Index: 1428134 (Python Code)

Max Activating Token Index: 140

Text #15

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1101. Min Act: -0.0002

Data Index: 1596041 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1054. Min Act: -0.0003

Data Index: 1424338 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1048. Min Act: -0.0003

Data Index: 1510022 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1010. Min Act: -0.0003

Data Index: 1643592 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1437635 (Python Code)

Max Activating Token Index: 142