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

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

Neuron 2711 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0716. Min Range: -1.0716

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1181903 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 1.0716. Min Range: -1.0716

Max Act: 1.0716. Min Act: -0.0000

Data Index: 904102 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9929. Min Act: -0.0000

Data Index: 775919 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1341670 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9389. Min Act: -0.0000

Data Index: 67321 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9063. Min Act: -0.0000

Data Index: 955410 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9091. Min Act: -0.0000

Data Index: 31249 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9579. Min Act: -0.0000

Data Index: 2202 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9542. Min Act: -0.0000

Data Index: 947467 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1546697 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9065. Min Act: -0.0000

Data Index: 713401 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1422480 (Python Code)

Max Activating Token Index: 873

Text #12

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1009399 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1140072 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1382290 (Python Code)

Max Activating Token Index: 776

Text #15

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8028. Min Act: -0.0000

Data Index: 406823 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8033. Min Act: -0.0000

Data Index: 221649 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.7996. Min Act: -0.0000

Data Index: 5740 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.7642. Min Act: 0.0000

Data Index: 139466 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.7431. Min Act: -0.0000

Data Index: 394000 (C4 (Web Text))

Max Activating Token Index: 865