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

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

Neuron 5700 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0581. Min Range: -4.0581

Max Act: 4.0581. Min Act: -0.0000

Data Index: 138422 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.6580. Min Act: -0.0000

Data Index: 339516 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.9815. Min Act: -0.0000

Data Index: 190285 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.7098. Min Act: -0.0000

Data Index: 256956 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.7303. Min Act: -0.0000

Data Index: 361057 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.5043. Min Act: -0.0000

Data Index: 677834 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.6739. Min Act: -0.0000

Data Index: 1177067 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.6023. Min Act: -0.0000

Data Index: 645837 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.5625. Min Act: -0.0000

Data Index: 1312732 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.1515. Min Act: -0.0000

Data Index: 233454 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.0427. Min Act: -0.0000

Data Index: 713933 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 4.0581. Min Range: -4.0581

Max Act: 2.9243. Min Act: -0.0000

Data Index: 1029742 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 4.0581. Min Range: -4.0581

Max Act: 3.1645. Min Act: -0.0000

Data Index: 775961 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 4.0581. Min Range: -4.0581

Max Act: 2.7111. Min Act: -0.0000

Data Index: 1289397 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 4.0581. Min Range: -4.0581

Max Act: 2.7928. Min Act: -0.0000

Data Index: 683166 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 4.0581. Min Range: -4.0581

Max Act: 2.6707. Min Act: -0.0000

Data Index: 384187 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 4.0581. Min Range: -4.0581

Max Act: 2.5082. Min Act: -0.0000

Data Index: 589482 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 4.0581. Min Range: -4.0581

Max Act: 2.3280. Min Act: -0.0000

Data Index: 270898 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 4.0581. Min Range: -4.0581

Max Act: 2.7908. Min Act: -0.0000

Data Index: 1183075 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 4.0581. Min Range: -4.0581

Max Act: 2.1428. Min Act: -0.0000

Data Index: 426608 (C4 (Web Text))

Max Activating Token Index: 712