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

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

Neuron 1198 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: 6.3650. Min Range: -6.3650

Max Act: 6.3650. Min Act: -0.0000

Data Index: 1219799 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 6.3650. Min Range: -6.3650

Max Act: 5.3123. Min Act: -0.0000

Data Index: 1037650 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.8836. Min Act: -0.0000

Data Index: 1106114 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 6.3650. Min Range: -6.3650

Max Act: 5.1985. Min Act: -0.0000

Data Index: 232561 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 6.3650. Min Range: -6.3650

Max Act: 5.0459. Min Act: -0.0000

Data Index: 1302721 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.8144. Min Act: -0.0000

Data Index: 877306 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.6214. Min Act: -0.0000

Data Index: 177041 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.6726. Min Act: -0.0000

Data Index: 60554 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.7280. Min Act: -0.0000

Data Index: 307887 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.5441. Min Act: -0.0000

Data Index: 960835 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.3447. Min Act: -0.0000

Data Index: 1052718 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.4932. Min Act: -0.0000

Data Index: 465917 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.7408. Min Act: -0.0000

Data Index: 152845 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.4294. Min Act: -0.0000

Data Index: 1478506 (Python Code)

Max Activating Token Index: 319

Text #14

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.2951. Min Act: -0.0000

Data Index: 921776 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.0699. Min Act: -0.0000

Data Index: 889672 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.2976. Min Act: -0.0000

Data Index: 778729 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.0984. Min Act: -0.0000

Data Index: 747460 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 6.3650. Min Range: -6.3650

Max Act: 4.0741. Min Act: -0.0000

Data Index: 208876 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 6.3650. Min Range: -6.3650

Max Act: 3.8963. Min Act: -0.0000

Data Index: 1044857 (C4 (Web Text))

Max Activating Token Index: 546