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

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

Neuron 5031 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.4398. Min Range: -10.4398

Max Act: 10.4398. Min Act: -0.0000

Data Index: 13237 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 10.4398. Min Range: -10.4398

Max Act: 10.0397. Min Act: -0.0000

Data Index: 67239 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 10.4398. Min Range: -10.4398

Max Act: 9.1375. Min Act: -0.0000

Data Index: 1307471 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.8305. Min Act: -0.0000

Data Index: 818527 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.6468. Min Act: -0.0000

Data Index: 1029773 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.2313. Min Act: -0.0000

Data Index: 884455 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.6987. Min Act: -0.0000

Data Index: 172867 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.3248. Min Act: -0.0000

Data Index: 217113 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.1480. Min Act: -0.0000

Data Index: 594363 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.1097. Min Act: -0.0000

Data Index: 127624 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.0394. Min Act: -0.0000

Data Index: 1140897 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.0011. Min Act: -0.0000

Data Index: 820147 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 10.4398. Min Range: -10.4398

Max Act: 7.9623. Min Act: -0.0000

Data Index: 25424 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 10.4398. Min Range: -10.4398

Max Act: 7.9451. Min Act: -0.0000

Data Index: 1119927 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 10.4398. Min Range: -10.4398

Max Act: 8.0715. Min Act: -0.0000

Data Index: 208488 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 10.4398. Min Range: -10.4398

Max Act: 7.8238. Min Act: -0.0000

Data Index: 766454 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 10.4398. Min Range: -10.4398

Max Act: 7.9647. Min Act: -0.0000

Data Index: 1026199 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 10.4398. Min Range: -10.4398

Max Act: 7.4712. Min Act: -0.0000

Data Index: 1160253 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 10.4398. Min Range: -10.4398

Max Act: 7.7610. Min Act: -0.0000

Data Index: 649096 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 10.4398. Min Range: -10.4398

Max Act: 7.5296. Min Act: -0.0000

Data Index: 1075096 (C4 (Web Text))

Max Activating Token Index: 877