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

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

Neuron 1892 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.4883. Min Act: -0.0001

Data Index: 1024789 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.4483. Min Act: -0.0001

Data Index: 171134 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3140. Min Act: -0.0001

Data Index: 172780 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3571. Min Act: -0.0001

Data Index: 1329893 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3505. Min Act: -0.0001

Data Index: 785661 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3262. Min Act: -0.0001

Data Index: 347089 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3119. Min Act: -0.0001

Data Index: 423148 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3150. Min Act: -0.0001

Data Index: 16674 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3078. Min Act: -0.0001

Data Index: 11132 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3140. Min Act: -0.0001

Data Index: 721643 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.2843. Min Act: -0.0001

Data Index: 430358 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.2956. Min Act: -0.0001

Data Index: 545975 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.2698. Min Act: -0.0001

Data Index: 109169 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3012. Min Act: -0.0001

Data Index: 606971 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.2987. Min Act: -0.0001

Data Index: 25624 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.2749. Min Act: -0.0001

Data Index: 773825 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.2940. Min Act: -0.0001

Data Index: 544253 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.2759. Min Act: -0.0001

Data Index: 510953 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.3263. Min Act: -0.0001

Data Index: 544981 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.4883. Min Range: -0.4883

Max Act: 0.2918. Min Act: -0.0001

Data Index: 921339 (C4 (Web Text))

Max Activating Token Index: 655