Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 33 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5914. Min Act: -0.0001

Data Index: 28494 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5324. Min Act: -0.0001

Data Index: 288218 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5768. Min Act: -0.0001

Data Index: 960265 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4981. Min Act: -0.0001

Data Index: 1346465 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1197196 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4474. Min Act: -0.0001

Data Index: 734507 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4799. Min Act: -0.0001

Data Index: 838016 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4569. Min Act: -0.0001

Data Index: 38043 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5690. Min Act: -0.0001

Data Index: 774642 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4382. Min Act: -0.0001

Data Index: 869758 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5343. Min Act: -0.0001

Data Index: 458751 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5187. Min Act: -0.0001

Data Index: 344054 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4263. Min Act: -0.0001

Data Index: 367898 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4677. Min Act: -0.0001

Data Index: 50360 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5069. Min Act: -0.0001

Data Index: 259020 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4666. Min Act: -0.0001

Data Index: 607371 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4807. Min Act: -0.0001

Data Index: 437328 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4756. Min Act: -0.0001

Data Index: 362402 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4357. Min Act: -0.0001

Data Index: 1250231 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1326912 (C4 (Web Text))

Max Activating Token Index: 258