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

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

Neuron 4029 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1193. Min Act: -0.0002

Data Index: 1556955 (Python Code)

Max Activating Token Index: 390

Text #1

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1410983 (Python Code)

Max Activating Token Index: 412

Text #2

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1369034 (Python Code)

Max Activating Token Index: 480

Text #3

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1583146 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1548104 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1485392 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1552062 (Python Code)

Max Activating Token Index: 100

Text #7

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1632558 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1598660 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1393779 (Python Code)

Max Activating Token Index: 303

Text #10

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1464338 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1488608 (Python Code)

Max Activating Token Index: 488

Text #12

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1428731 (Python Code)

Max Activating Token Index: 447

Text #13

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1575566 (Python Code)

Max Activating Token Index: 170

Text #14

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1364011 (Python Code)

Max Activating Token Index: 681

Text #15

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1619618 (Python Code)

Max Activating Token Index: 549

Text #16

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1504549 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1445659 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1370716 (Python Code)

Max Activating Token Index: 154

Text #19

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1440794 (Python Code)

Max Activating Token Index: 72