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

Dataset: The Pile

Neuron 3056 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.8487. Min Act: -0.0000

Data Index: 1130998 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1192744 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.4024. Min Act: -0.0000

Data Index: 1081367 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3667. Min Act: -0.0000

Data Index: 1951389 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3352. Min Act: -0.0000

Data Index: 492005 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3642. Min Act: -0.0000

Data Index: 704783 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.2709. Min Act: -0.0000

Data Index: 1877095 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.2323. Min Act: -0.0000

Data Index: 549901 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1903019 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.1573. Min Act: -0.0000

Data Index: 703938 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1463251 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.1195. Min Act: -0.0000

Data Index: 18692 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 1.8487. Min Range: -1.8487

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1948507 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1393050 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.0693. Min Act: -0.0000

Data Index: 827197 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1333205 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.0451. Min Act: -0.0000

Data Index: 986527 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.0450. Min Act: -0.0000

Data Index: 385400 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.0430. Min Act: -0.0000

Data Index: 299716 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.0726. Min Act: -0.0000

Data Index: 419942 (The Pile)

Max Activating Token Index: 369