Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5108 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0168. Min Range: -2.0168

Max Act: 2.0168. Min Act: -0.0000

Data Index: 1087373 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.8740. Min Act: -0.0000

Data Index: 601783 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.9036. Min Act: -0.0000

Data Index: 1055465 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.7053. Min Act: -0.0000

Data Index: 574291 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.6805. Min Act: -0.0000

Data Index: 565441 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.5568. Min Act: -0.0000

Data Index: 123172 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.5593. Min Act: -0.0000

Data Index: 56257 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.4276. Min Act: -0.0000

Data Index: 780614 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.3903. Min Act: -0.0000

Data Index: 740685 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.4552. Min Act: -0.0000

Data Index: 1329829 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1088502 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.4414. Min Act: -0.0000

Data Index: 447530 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.4013. Min Act: -0.0000

Data Index: 699873 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.3999. Min Act: -0.0000

Data Index: 443177 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.2986. Min Act: -0.0000

Data Index: 87892 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.3430. Min Act: -0.0000

Data Index: 173940 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.2246. Min Act: -0.0000

Data Index: 623204 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1100160 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.3587. Min Act: -0.0000

Data Index: 447193 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 2.0168. Min Range: -2.0168

Max Act: 1.3475. Min Act: -0.0000

Data Index: 357043 (C4 (Web Text))

Max Activating Token Index: 677