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

Dataset: The Pile

Neuron 4092 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: 0.5209. Min Range: -0.5209

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1746778 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4033. Min Act: -0.0000

Data Index: 228951 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4771. Min Act: -0.0000

Data Index: 257974 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4611. Min Act: -0.0000

Data Index: 711018 (The Pile)

Max Activating Token Index: 979

Text #4

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4988. Min Act: -0.0000

Data Index: 489089 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1295677 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1660703 (The Pile)

Max Activating Token Index: 570

Text #7

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1517129 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1377942 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1862519 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4354. Min Act: -0.0000

Data Index: 535116 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1187199 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4168. Min Act: -0.0000

Data Index: 261814 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4381. Min Act: -0.0000

Data Index: 282868 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1172954 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.5065. Min Act: -0.0000

Data Index: 479426 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1581077 (The Pile)

Max Activating Token Index: 306

Text #17

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4199. Min Act: -0.0000

Data Index: 489862 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1490393 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1770647 (The Pile)

Max Activating Token Index: 595