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

Dataset: The Pile

Neuron 1792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1051423 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.6230. Min Act: -0.0000

Data Index: 976397 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5589. Min Act: -0.0000

Data Index: 404694 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5200. Min Act: -0.0000

Data Index: 223459 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1336197 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1264939 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1017360 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4864. Min Act: -0.0000

Data Index: 244266 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4628. Min Act: -0.0000

Data Index: 679581 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1592809 (The Pile)

Max Activating Token Index: 174

Text #10

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1157710 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1840604 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1483079 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1846808 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1493023 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3717. Min Act: -0.0000

Data Index: 226595 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3844. Min Act: -0.0000

Data Index: 334141 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1786555 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3648. Min Act: -0.0000

Data Index: 994783 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1113989 (The Pile)

Max Activating Token Index: 670