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

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

Neuron 21 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1617514 (Python Code)

Max Activating Token Index: 739

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1617791 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1564153 (Python Code)

Max Activating Token Index: 426

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1361165 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1397664 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1361354 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1412038 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1360013 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1544325 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1453471 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1462215 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1625107 (Python Code)

Max Activating Token Index: 797

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1429782 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1385558 (Python Code)

Max Activating Token Index: 421

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1578716 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1625350 (Python Code)

Max Activating Token Index: 621

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1614307 (Python Code)

Max Activating Token Index: 492

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1556919 (Python Code)

Max Activating Token Index: 348

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1583336 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1628667 (Python Code)

Max Activating Token Index: 172