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

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

Neuron 1256 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1039273 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3782. Min Act: -0.0000

Data Index: 732448 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1161383 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1308606 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3169. Min Act: -0.0000

Data Index: 537580 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3019. Min Act: -0.0000

Data Index: 813280 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2987. Min Act: -0.0000

Data Index: 126439 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1137576 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1313508 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2671. Min Act: -0.0000

Data Index: 970198 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2527. Min Act: -0.0000

Data Index: 97999 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2236. Min Act: -0.0000

Data Index: 333062 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2448. Min Act: -0.0000

Data Index: 795067 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2465. Min Act: -0.0000

Data Index: 849190 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2439. Min Act: -0.0000

Data Index: 927175 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2337. Min Act: -0.0000

Data Index: 449698 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2298. Min Act: -0.0000

Data Index: 369635 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2302. Min Act: -0.0000

Data Index: 172474 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2164. Min Act: -0.0000

Data Index: 796723 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2235. Min Act: -0.0000

Data Index: 144892 (C4 (Web Text))

Max Activating Token Index: 310