Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 50 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.4484. Min Act: -0.0000

Data Index: 445275 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.4221. Min Act: -0.0000

Data Index: 598577 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.2890. Min Act: -0.0000

Data Index: 336039 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.3337. Min Act: -0.0000

Data Index: 51237 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1510236 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1438870 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1032078 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.2097. Min Act: -0.0000

Data Index: 920936 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1845. Min Act: -0.0001

Data Index: 662259 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1773. Min Act: -0.0000

Data Index: 817534 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1242723 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1118889 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0541. Min Act: -0.0000

Data Index: 1316188 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.2024. Min Act: -0.0000

Data Index: 653581 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1225. Min Act: -0.0001

Data Index: 244827 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1670. Min Act: -0.0000

Data Index: 962193 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0845. Min Act: -0.0000

Data Index: 495832 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1157. Min Act: -0.0001

Data Index: 368906 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0823. Min Act: -0.0000

Data Index: 347047 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1123694 (C4 (Web Text))

Max Activating Token Index: 383