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

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

Neuron 3893 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.2436. Min Act: -0.0003

Data Index: 1060978 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.1871. Min Act: -0.0003

Data Index: 524685 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.0357. Min Act: -0.0003

Data Index: 286836 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.0102. Min Act: -0.0003

Data Index: 24418 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9733. Min Act: -0.0003

Data Index: 562349 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.0030. Min Act: -0.0003

Data Index: 636497 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.2436. Min Range: -1.2436

Max Act: 1.0034. Min Act: -0.0002

Data Index: 1295174 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9773. Min Act: -0.0003

Data Index: 1315922 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9453. Min Act: -0.0003

Data Index: 959555 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9712. Min Act: -0.0003

Data Index: 43937 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9634. Min Act: -0.0003

Data Index: 689920 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9332. Min Act: -0.0003

Data Index: 370111 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9894. Min Act: -0.0003

Data Index: 348075 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9530. Min Act: -0.0003

Data Index: 56422 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9486. Min Act: -0.0003

Data Index: 204901 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9429. Min Act: -0.0003

Data Index: 156044 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9349. Min Act: -0.0003

Data Index: 670456 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9697. Min Act: -0.0003

Data Index: 599503 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9542. Min Act: -0.0003

Data Index: 1215262 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 1.2436. Min Range: -1.2436

Max Act: 0.9273. Min Act: -0.0003

Data Index: 1144630 (C4 (Web Text))

Max Activating Token Index: 467