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

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

Neuron 796 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: 0.0212. Min Range: -0.0212

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1514307 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1478415 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1401020 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1572715 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1434291 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1469517 (Python Code)

Max Activating Token Index: 919

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1619714 (Python Code)

Max Activating Token Index: 767

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1485896 (Python Code)

Max Activating Token Index: 945

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1548417 (Python Code)

Max Activating Token Index: 406

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1428086 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1443204 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1478234 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1450666 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1362674 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1465675 (Python Code)

Max Activating Token Index: 507

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1369863 (Python Code)

Max Activating Token Index: 612

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1465869 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1579951 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1443508 (Python Code)

Max Activating Token Index: 376

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1543927 (Python Code)

Max Activating Token Index: 988