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

Dataset: The Pile

Neuron 1951 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1742645 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1222502 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0975. Min Act: -0.0000

Data Index: 748261 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0986. Min Act: -0.0000

Data Index: 917321 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1217128 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0917. Min Act: -0.0000

Data Index: 893610 (The Pile)

Max Activating Token Index: 769

Text #6

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1082951 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1542330 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1466818 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0898. Min Act: -0.0000

Data Index: 716316 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0835. Min Act: -0.0000

Data Index: 517579 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0853. Min Act: -0.0000

Data Index: 895715 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1274301 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1092465 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1381351 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0796. Min Act: -0.0000

Data Index: 689096 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1120255 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0730. Min Act: -0.0000

Data Index: 365348 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1370321 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0776. Min Act: -0.0000

Data Index: 236392 (The Pile)

Max Activating Token Index: 767