Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1559 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1099499 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.4363. Min Act: -0.0001

Data Index: 689180 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.4182. Min Act: -0.0001

Data Index: 1304571 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1230875 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.4062. Min Act: -0.0001

Data Index: 304170 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3702. Min Act: -0.0001

Data Index: 1591651 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3832. Min Act: -0.0001

Data Index: 396906 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3711. Min Act: -0.0001

Data Index: 1266341 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3804. Min Act: -0.0001

Data Index: 975222 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3796. Min Act: -0.0001

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3897. Min Act: -0.0001

Data Index: 846541 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3864. Min Act: -0.0001

Data Index: 810796 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1329893 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3863. Min Act: -0.0001

Data Index: 1124163 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3594. Min Act: -0.0001

Data Index: 946193 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1481969 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3944. Min Act: -0.0001

Data Index: 679142 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3624. Min Act: -0.0001

Data Index: 1229036 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3754. Min Act: -0.0000

Data Index: 707361 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.4363. Min Range: -0.4363

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1215466 (C4 (Web Text))

Max Activating Token Index: 847