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

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

Neuron 2149 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6640. Min Act: -0.0000

Data Index: 520976 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1000423 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6258. Min Act: -0.0000

Data Index: 522055 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1059767 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1259011 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5425. Min Act: -0.0000

Data Index: 417721 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1186971 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5193. Min Act: -0.0000

Data Index: 151958 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1009344 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5652. Min Act: -0.0000

Data Index: 877411 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5442. Min Act: -0.0000

Data Index: 272122 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4932. Min Act: -0.0000

Data Index: 741274 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5558. Min Act: -0.0000

Data Index: 486916 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5048. Min Act: -0.0000

Data Index: 557095 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1035060 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5276. Min Act: -0.0000

Data Index: 947912 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5233. Min Act: -0.0000

Data Index: 907902 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5222. Min Act: -0.0000

Data Index: 23942 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5224. Min Act: -0.0000

Data Index: 87786 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5090. Min Act: -0.0000

Data Index: 579943 (C4 (Web Text))

Max Activating Token Index: 961