Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 842 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1559157 (Python Code)

Max Activating Token Index: 620

Text #1

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.7793. Min Act: -0.0001

Data Index: 1548714 (Python Code)

Max Activating Token Index: 551

Text #2

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.7274. Min Act: -0.0001

Data Index: 1469338 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.7172. Min Act: -0.0001

Data Index: 1489661 (Python Code)

Max Activating Token Index: 331

Text #4

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6498. Min Act: -0.0001

Data Index: 1391697 (Python Code)

Max Activating Token Index: 770

Text #5

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.7223. Min Act: -0.0001

Data Index: 1608075 (Python Code)

Max Activating Token Index: 169

Text #6

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.7199. Min Act: -0.0001

Data Index: 1556761 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6647. Min Act: -0.0001

Data Index: 1552740 (Python Code)

Max Activating Token Index: 524

Text #8

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1648771 (Python Code)

Max Activating Token Index: 899

Text #9

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6588. Min Act: -0.0001

Data Index: 1441563 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6484. Min Act: -0.0001

Data Index: 1651832 (Python Code)

Max Activating Token Index: 638

Text #11

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6744. Min Act: -0.0001

Data Index: 1449454 (Python Code)

Max Activating Token Index: 793

Text #12

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6168. Min Act: -0.0001

Data Index: 1507646 (Python Code)

Max Activating Token Index: 497

Text #13

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6190. Min Act: -0.0001

Data Index: 1656858 (Python Code)

Max Activating Token Index: 470

Text #14

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6178. Min Act: -0.0001

Data Index: 1460386 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6165. Min Act: -0.0001

Data Index: 1427813 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1488322 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5885. Min Act: -0.0001

Data Index: 1585136 (Python Code)

Max Activating Token Index: 940

Text #18

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6266. Min Act: -0.0001

Data Index: 1574252 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6016. Min Act: -0.0001

Data Index: 1637936 (Python Code)

Max Activating Token Index: 56