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

Dataset: The Pile

Neuron 1388 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.4283. Min Act: -0.0000

Data Index: 5571 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1482991 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.2592. Min Act: -0.0000

Data Index: 581002 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.3177. Min Act: -0.0000

Data Index: 1136600 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.2924. Min Act: -0.0000

Data Index: 1485078 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1039062 (The Pile)

Max Activating Token Index: 893

Text #6

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.2791. Min Act: -0.0000

Data Index: 1216239 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1160144 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.1807. Min Act: -0.0000

Data Index: 183117 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1184963 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.1583. Min Act: -0.0000

Data Index: 574808 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.2090. Min Act: -0.0000

Data Index: 375091 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.1396. Min Act: -0.0000

Data Index: 280587 (The Pile)

Max Activating Token Index: 67

Text #13

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.1474. Min Act: -0.0000

Data Index: 710425 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1959771 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.1113. Min Act: -0.0000

Data Index: 872925 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.1051. Min Act: -0.0000

Data Index: 916993 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1358956 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1539267 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1963905 (The Pile)

Max Activating Token Index: 123