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

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

Neuron 560 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7805. Min Act: -0.0000

Data Index: 993299 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7799. Min Act: -0.0000

Data Index: 707846 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1237880 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6810. Min Act: -0.0000

Data Index: 229900 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6606. Min Act: 0.0001

Data Index: 484904 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6331. Min Act: -0.0000

Data Index: 351593 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6227. Min Act: 0.0000

Data Index: 223090 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5961. Min Act: 0.0001

Data Index: 517503 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1092956 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5760. Min Act: -0.0000

Data Index: 388452 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1029705 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5845. Min Act: -0.0000

Data Index: 521920 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5790. Min Act: -0.0000

Data Index: 143583 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5390. Min Act: -0.0000

Data Index: 388665 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5435. Min Act: 0.0000

Data Index: 479243 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5163. Min Act: -0.0000

Data Index: 698824 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5398. Min Act: -0.0000

Data Index: 916779 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5491. Min Act: -0.0000

Data Index: 147212 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5274. Min Act: -0.0000

Data Index: 814634 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5099. Min Act: -0.0000

Data Index: 308116 (C4 (Web Text))

Max Activating Token Index: 713