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

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

Neuron 3463 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: 0.1864. Min Range: -0.1864

Max Act: 0.1864. Min Act: -0.0000

Data Index: 874469 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1693. Min Act: -0.0000

Data Index: 903270 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1044309 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1176113 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1437. Min Act: -0.0000

Data Index: 414979 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1463. Min Act: -0.0000

Data Index: 578735 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1467. Min Act: -0.0000

Data Index: 422830 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1377. Min Act: -0.0000

Data Index: 399629 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1332. Min Act: -0.0000

Data Index: 595295 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1368. Min Act: -0.0000

Data Index: 376062 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1331958 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1253. Min Act: -0.0000

Data Index: 211094 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1332. Min Act: -0.0000

Data Index: 589685 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1245. Min Act: -0.0000

Data Index: 264658 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1197. Min Act: -0.0000

Data Index: 1326421 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1233. Min Act: -0.0000

Data Index: 356710 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1230. Min Act: -0.0000

Data Index: 886122 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1186. Min Act: -0.0000

Data Index: 449915 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1270. Min Act: -0.0000

Data Index: 856806 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1282. Min Act: -0.0000

Data Index: 637669 (C4 (Web Text))

Max Activating Token Index: 1012