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

Dataset: The Pile

Neuron 2152 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1706. Min Act: -0.0000

Data Index: 65719 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1792122 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1331625 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1861615 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1388159 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1080613 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1011. Min Act: -0.0000

Data Index: 471374 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1024. Min Act: -0.0000

Data Index: 514493 (The Pile)

Max Activating Token Index: 865

Text #8

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1225828 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1450728 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1686644 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1008. Min Act: -0.0000

Data Index: 85387 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1107. Min Act: -0.0000

Data Index: 987351 (The Pile)

Max Activating Token Index: 718

Text #13

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1022. Min Act: -0.0000

Data Index: 876624 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1086. Min Act: -0.0000

Data Index: 862462 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1016. Min Act: -0.0000

Data Index: 988446 (The Pile)

Max Activating Token Index: 159

Text #16

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1046. Min Act: -0.0000

Data Index: 668468 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1030. Min Act: -0.0000

Data Index: 876199 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1262. Min Act: -0.0000

Data Index: 5129 (The Pile)

Max Activating Token Index: 840

Text #19

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1623437 (The Pile)

Max Activating Token Index: 413