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

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

Neuron 559 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: 0.6231. Min Range: -0.6231

Max Act: 0.6056. Min Act: -0.0003

Data Index: 1394340 (Python Code)

Max Activating Token Index: 320

Text #1

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.6060. Min Act: -0.0003

Data Index: 1500153 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.6220. Min Act: -0.0003

Data Index: 1420311 (Python Code)

Max Activating Token Index: 407

Text #3

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.6194. Min Act: -0.0003

Data Index: 1493049 (Python Code)

Max Activating Token Index: 356

Text #4

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.6160. Min Act: -0.0003

Data Index: 1596172 (Python Code)

Max Activating Token Index: 674

Text #5

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5844. Min Act: -0.0003

Data Index: 1360133 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.6231. Min Act: -0.0003

Data Index: 1479365 (Python Code)

Max Activating Token Index: 204

Text #7

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5840. Min Act: -0.0003

Data Index: 1621834 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5740. Min Act: -0.0003

Data Index: 1444473 (Python Code)

Max Activating Token Index: 685

Text #9

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5772. Min Act: -0.0003

Data Index: 1482996 (Python Code)

Max Activating Token Index: 101

Text #10

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5743. Min Act: -0.0003

Data Index: 1451446 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5889. Min Act: -0.0003

Data Index: 1430038 (Python Code)

Max Activating Token Index: 191

Text #12

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5518. Min Act: -0.0003

Data Index: 1366438 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5703. Min Act: -0.0003

Data Index: 1470816 (Python Code)

Max Activating Token Index: 578

Text #14

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5198. Min Act: -0.0003

Data Index: 1470350 (Python Code)

Max Activating Token Index: 142

Text #15

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5718. Min Act: -0.0003

Data Index: 1420684 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5284. Min Act: -0.0003

Data Index: 1426082 (Python Code)

Max Activating Token Index: 455

Text #17

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4997. Min Act: -0.0003

Data Index: 1490583 (Python Code)

Max Activating Token Index: 205

Text #18

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5156. Min Act: -0.0003

Data Index: 1377124 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5191. Min Act: -0.0003

Data Index: 1384379 (Python Code)

Max Activating Token Index: 750