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

Dataset: The Pile

Neuron 1203 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2555. Min Act: -0.0001

Data Index: 1363413 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2024. Min Act: -0.0001

Data Index: 584770 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1296712 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1160592 (The Pile)

Max Activating Token Index: 571

Text #4

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2029. Min Act: -0.0001

Data Index: 1062988 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2064. Min Act: -0.0001

Data Index: 1177713 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1954. Min Act: -0.0001

Data Index: 1601 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1904. Min Act: -0.0001

Data Index: 1335410 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1920. Min Act: -0.0001

Data Index: 971606 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1869. Min Act: -0.0001

Data Index: 1181010 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1925. Min Act: -0.0001

Data Index: 764290 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1828. Min Act: -0.0001

Data Index: 1124171 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1909. Min Act: -0.0001

Data Index: 152980 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1001614 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1373504 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1383925 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1534702 (The Pile)

Max Activating Token Index: 815

Text #17

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1754. Min Act: -0.0001

Data Index: 1095200 (The Pile)

Max Activating Token Index: 871

Text #18

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1431117 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1775. Min Act: -0.0001

Data Index: 182252 (The Pile)

Max Activating Token Index: 178