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

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

Neuron 442 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: 0.4563. Min Range: -0.4563

Max Act: 0.4563. Min Act: -0.0001

Data Index: 739399 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3847. Min Act: -0.0001

Data Index: 934825 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3324. Min Act: -0.0001

Data Index: 96128 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3403. Min Act: -0.0001

Data Index: 946039 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1012003 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3172. Min Act: -0.0001

Data Index: 1224262 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3244. Min Act: -0.0001

Data Index: 1000093 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3013. Min Act: -0.0001

Data Index: 162505 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3187. Min Act: -0.0001

Data Index: 1036898 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3035. Min Act: -0.0001

Data Index: 191406 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3128. Min Act: -0.0001

Data Index: 45727 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3002. Min Act: -0.0001

Data Index: 967249 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.3080. Min Act: -0.0001

Data Index: 240775 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.2829. Min Act: -0.0001

Data Index: 323799 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1019856 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.2636. Min Act: -0.0001

Data Index: 64851 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.2724. Min Act: -0.0001

Data Index: 24415 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.2802. Min Act: -0.0001

Data Index: 299643 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.2975. Min Act: -0.0001

Data Index: 417860 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.4563. Min Range: -0.4563

Max Act: 0.2844. Min Act: -0.0001

Data Index: 1127778 (C4 (Web Text))

Max Activating Token Index: 1009