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

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

Neuron 3946 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0168. Min Range: -3.0168

Max Act: 3.0168. Min Act: -0.0000

Data Index: 257913 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.9525. Min Act: -0.0000

Data Index: 587427 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.5220. Min Act: -0.0000

Data Index: 505224 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.3204. Min Act: -0.0000

Data Index: 681738 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.0746. Min Act: -0.0000

Data Index: 1040252 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.1786. Min Act: -0.0000

Data Index: 1296605 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.3781. Min Act: -0.0000

Data Index: 475991 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.3710. Min Act: -0.0000

Data Index: 123463 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.2285. Min Act: -0.0000

Data Index: 529908 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.1425. Min Act: -0.0000

Data Index: 201956 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.1177. Min Act: -0.0000

Data Index: 214981 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.1064. Min Act: -0.0000

Data Index: 295319 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 3.0168. Min Range: -3.0168

Max Act: 1.9734. Min Act: -0.0000

Data Index: 5268 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.1864. Min Act: -0.0000

Data Index: 1141804 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 3.0168. Min Range: -3.0168

Max Act: 1.9679. Min Act: -0.0000

Data Index: 1218702 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.1177. Min Act: -0.0000

Data Index: 940959 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 3.0168. Min Range: -3.0168

Max Act: 1.9745. Min Act: -0.0000

Data Index: 624267 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 3.0168. Min Range: -3.0168

Max Act: 1.9409. Min Act: -0.0000

Data Index: 1257189 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 3.0168. Min Range: -3.0168

Max Act: 1.8444. Min Act: -0.0000

Data Index: 1237302 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 3.0168. Min Range: -3.0168

Max Act: 2.1352. Min Act: -0.0000

Data Index: 697141 (C4 (Web Text))

Max Activating Token Index: 520