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

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

Neuron 5062 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.1058. Min Act: -0.0001

Data Index: 966102 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1328498 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0886. Min Act: -0.0001

Data Index: 496619 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0896. Min Act: -0.0001

Data Index: 495787 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0962. Min Act: -0.0001

Data Index: 859487 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1055837 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0900. Min Act: -0.0001

Data Index: 537231 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1271674 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0890. Min Act: -0.0001

Data Index: 626730 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1116913 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1173550 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0888. Min Act: -0.0001

Data Index: 500837 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0874. Min Act: -0.0001

Data Index: 334013 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0878. Min Act: -0.0001

Data Index: 1049449 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0866. Min Act: -0.0001

Data Index: 377631 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1195755 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1094704 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0828. Min Act: -0.0001

Data Index: 316769 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0886. Min Act: -0.0001

Data Index: 179331 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0864. Min Act: -0.0001

Data Index: 975441 (C4 (Web Text))

Max Activating Token Index: 65