Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 612 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1101624 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7211. Min Act: -0.0000

Data Index: 18134 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6881. Min Act: 0.0000

Data Index: 672446 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1132331 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6279. Min Act: -0.0000

Data Index: 727476 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6499. Min Act: 0.0000

Data Index: 704843 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6363. Min Act: -0.0000

Data Index: 577089 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1289767 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6038. Min Act: -0.0000

Data Index: 356526 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6505. Min Act: -0.0000

Data Index: 643278 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6228. Min Act: -0.0000

Data Index: 859357 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6164. Min Act: -0.0000

Data Index: 297108 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6252. Min Act: 0.0000

Data Index: 881407 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6161. Min Act: -0.0000

Data Index: 901729 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6029. Min Act: -0.0000

Data Index: 271770 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5271. Min Act: 0.0000

Data Index: 503663 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1183645 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5434. Min Act: -0.0000

Data Index: 315139 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4881. Min Act: -0.0000

Data Index: 147648 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5213. Min Act: 0.0001

Data Index: 437593 (C4 (Web Text))

Max Activating Token Index: 786