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

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

Neuron 3357 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1543374 (Python Code)

Max Activating Token Index: 878

Text #1

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1571197 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1533059 (Python Code)

Max Activating Token Index: 323

Text #3

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1655246 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1436392 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1494971 (Python Code)

Max Activating Token Index: 921

Text #6

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1429490 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1483012 (Python Code)

Max Activating Token Index: 93

Text #8

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1489059 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1435679 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1445702 (Python Code)

Max Activating Token Index: 829

Text #11

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1638948 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1443107 (Python Code)

Max Activating Token Index: 57

Text #13

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1584676 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1648862 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1560380 (Python Code)

Max Activating Token Index: 320

Text #16

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1614607 (Python Code)

Max Activating Token Index: 278

Text #17

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1636520 (Python Code)

Max Activating Token Index: 103

Text #18

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1389884 (Python Code)

Max Activating Token Index: 123

Text #19

Max Range: 0.6370. Min Range: -0.6370

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1370301 (Python Code)

Max Activating Token Index: 357