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

Dataset: The Pile

Neuron 4980 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.8609. Min Act: -0.0000

Data Index: 904870 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.8084. Min Act: -0.0000

Data Index: 314396 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.7855. Min Act: -0.0000

Data Index: 1665517 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.7077. Min Act: -0.0000

Data Index: 215807 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5788. Min Act: -0.0000

Data Index: 1545300 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.6174. Min Act: -0.0000

Data Index: 31722 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3559. Min Act: 0.0000

Data Index: 1168055 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3397. Min Act: -0.0000

Data Index: 599214 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1409468 (The Pile)

Max Activating Token Index: 563

Text #9

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.2708. Min Act: -0.0000

Data Index: 606480 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3241. Min Act: -0.0000

Data Index: 1114678 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1608187 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3168. Min Act: -0.0000

Data Index: 350325 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.4730. Min Act: -0.0000

Data Index: 1045543 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1183994 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1934351 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1796188 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.2503. Min Act: -0.0000

Data Index: 434720 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1281754 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1743725 (The Pile)

Max Activating Token Index: 41