Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1918 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3591. Min Act: -0.0001

Data Index: 781012 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3130. Min Act: -0.0001

Data Index: 1111067 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3321. Min Act: -0.0001

Data Index: 630880 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3140. Min Act: -0.0001

Data Index: 1127116 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3008. Min Act: -0.0001

Data Index: 138101 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3096. Min Act: -0.0001

Data Index: 666853 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3049. Min Act: -0.0001

Data Index: 1199876 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3256. Min Act: -0.0001

Data Index: 415823 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3149. Min Act: -0.0001

Data Index: 546566 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3145. Min Act: -0.0001

Data Index: 17376 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1253903 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3116. Min Act: -0.0001

Data Index: 1027811 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3083. Min Act: -0.0001

Data Index: 287767 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3055. Min Act: -0.0001

Data Index: 121456 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2952. Min Act: -0.0001

Data Index: 434256 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3143. Min Act: -0.0001

Data Index: 554207 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3142. Min Act: -0.0001

Data Index: 227582 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3016. Min Act: -0.0001

Data Index: 872 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3109. Min Act: -0.0001

Data Index: 493761 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2776. Min Act: -0.0001

Data Index: 1006186 (C4 (Web Text))

Max Activating Token Index: 688