Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1906 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1151550 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1084835 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0871. Min Act: -0.0002

Data Index: 647006 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1133161 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1055025 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0864. Min Act: -0.0002

Data Index: 691298 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0867. Min Act: -0.0002

Data Index: 913678 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0864. Min Act: -0.0002

Data Index: 160298 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0866. Min Act: -0.0002

Data Index: 94098 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0856. Min Act: -0.0001

Data Index: 518516 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1189937 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0820. Min Act: -0.0002

Data Index: 858643 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0848. Min Act: -0.0001

Data Index: 381312 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0844. Min Act: -0.0001

Data Index: 519135 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0845. Min Act: -0.0002

Data Index: 167469 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1136646 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1217630 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0873. Min Act: -0.0002

Data Index: 725331 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0861. Min Act: -0.0002

Data Index: 779113 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0822. Min Act: -0.0002

Data Index: 61363 (C4 (Web Text))

Max Activating Token Index: 13