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

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

Neuron 2650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0111. Min Range: -1.0111

Max Act: 1.0111. Min Act: -0.0000

Data Index: 559915 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.8139. Min Act: -0.0000

Data Index: 572891 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1075498 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7269. Min Act: -0.0000

Data Index: 472129 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7056. Min Act: -0.0000

Data Index: 328907 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6766. Min Act: -0.0000

Data Index: 841160 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6357. Min Act: -0.0000

Data Index: 726843 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6931. Min Act: -0.0000

Data Index: 873193 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1301030 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6697. Min Act: -0.0000

Data Index: 778681 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6652. Min Act: -0.0000

Data Index: 793665 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6388. Min Act: -0.0000

Data Index: 440982 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1226780 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6042. Min Act: -0.0000

Data Index: 843974 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6263. Min Act: -0.0000

Data Index: 610363 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6250. Min Act: -0.0000

Data Index: 564866 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6214. Min Act: -0.0000

Data Index: 574219 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6199. Min Act: -0.0000

Data Index: 333137 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6230. Min Act: -0.0000

Data Index: 569996 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6562. Min Act: -0.0000

Data Index: 915067 (C4 (Web Text))

Max Activating Token Index: 861