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

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

Neuron 526 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: 2.2877. Min Range: -2.2877

Max Act: 2.2877. Min Act: -0.0000

Data Index: 561925 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 2.2877. Min Range: -2.2877

Max Act: 2.0269. Min Act: -0.0000

Data Index: 615641 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 2.2877. Min Range: -2.2877

Max Act: 2.0015. Min Act: -0.0000

Data Index: 987260 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.9905. Min Act: -0.0000

Data Index: 808160 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.8071. Min Act: -0.0000

Data Index: 1253294 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.7983. Min Act: -0.0000

Data Index: 433343 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.7704. Min Act: -0.0000

Data Index: 1294152 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.6724. Min Act: -0.0000

Data Index: 932444 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.7195. Min Act: -0.0000

Data Index: 78606 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.4926. Min Act: -0.0000

Data Index: 52882 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.4648. Min Act: -0.0000

Data Index: 810491 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.6285. Min Act: -0.0000

Data Index: 804009 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.4670. Min Act: -0.0000

Data Index: 155187 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.5183. Min Act: -0.0000

Data Index: 45392 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.6090. Min Act: -0.0000

Data Index: 88092 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.4891. Min Act: -0.0000

Data Index: 257393 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.5758. Min Act: -0.0000

Data Index: 1065088 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.4785. Min Act: -0.0000

Data Index: 661660 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1285993 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 2.2877. Min Range: -2.2877

Max Act: 1.4705. Min Act: -0.0000

Data Index: 341677 (C4 (Web Text))

Max Activating Token Index: 654