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

Dataset: The Pile

Neuron 4572 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.7170. Min Act: -0.0000

Data Index: 535636 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.5966. Min Act: -0.0000

Data Index: 1803633 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.6903. Min Act: -0.0000

Data Index: 1590768 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.5866. Min Act: -0.0000

Data Index: 1666304 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.4120. Min Act: 0.0000

Data Index: 1721373 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1432821 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.2693. Min Act: -0.0000

Data Index: 195578 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.3165. Min Act: -0.0000

Data Index: 1525644 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1320391 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1689742 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1686645 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.0930. Min Act: -0.0000

Data Index: 870021 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.4384. Min Act: -0.0000

Data Index: 901658 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.1420. Min Act: -0.0000

Data Index: 134503 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.2881. Min Act: -0.0000

Data Index: 1130920 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1066055 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.2062. Min Act: -0.0000

Data Index: 58761 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1178109 (The Pile)

Max Activating Token Index: 920

Text #18

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1068065 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.2346. Min Act: -0.0000

Data Index: 786892 (The Pile)

Max Activating Token Index: 693