Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1989 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.2139. Min Act: -0.0001

Data Index: 1350620 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.4289. Min Act: -0.0001

Data Index: 475473 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1061257 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1913. Min Act: -0.0000

Data Index: 8861 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.2332. Min Act: -0.0001

Data Index: 1019802 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1444. Min Act: -0.0000

Data Index: 397457 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1324. Min Act: -0.0000

Data Index: 82074 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.2469. Min Act: -0.0000

Data Index: 181081 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.2303. Min Act: -0.0000

Data Index: 931788 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1778. Min Act: -0.0000

Data Index: 3102 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1120. Min Act: -0.0000

Data Index: 740133 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.2071. Min Act: -0.0001

Data Index: 969349 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1722. Min Act: -0.0001

Data Index: 171107 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1266. Min Act: -0.0000

Data Index: 956190 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1145. Min Act: -0.0000

Data Index: 360490 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.0841. Min Act: -0.0001

Data Index: 736731 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1028. Min Act: -0.0000

Data Index: 777200 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1047. Min Act: -0.0001

Data Index: 771046 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.0637. Min Act: -0.0001

Data Index: 595067 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1458. Min Act: -0.0000

Data Index: 689796 (C4 (Web Text))

Max Activating Token Index: 769