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

Dataset: The Pile

Neuron 221 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: 1.2118. Min Range: -1.2118

Max Act: 1.1453. Min Act: -0.0000

Data Index: 387547 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 1.2118. Min Range: -1.2118

Max Act: 1.2118. Min Act: -0.0000

Data Index: 346195 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 1.2118. Min Range: -1.2118

Max Act: 1.0508. Min Act: -0.0000

Data Index: 112769 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 1.2118. Min Range: -1.2118

Max Act: 1.0288. Min Act: -0.0000

Data Index: 860094 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.9889. Min Act: 0.0000

Data Index: 811714 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1962492 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.9643. Min Act: -0.0000

Data Index: 156261 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1985507 (The Pile)

Max Activating Token Index: 891

Text #8

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1950480 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1470393 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1497691 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.9403. Min Act: -0.0000

Data Index: 660941 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7770. Min Act: -0.0000

Data Index: 872110 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 1.2118. Min Range: -1.2118

Max Act: 1.0448. Min Act: -0.0000

Data Index: 566595 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 1.2118. Min Range: -1.2118

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1213668 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 1.2118. Min Range: -1.2118

Max Act: 1.1554. Min Act: -0.0000

Data Index: 737395 (The Pile)

Max Activating Token Index: 835

Text #16

Max Range: 1.2118. Min Range: -1.2118

Max Act: 1.0012. Min Act: -0.0000

Data Index: 85057 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.7524. Min Act: -0.0000

Data Index: 232533 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1639365 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 1.2118. Min Range: -1.2118

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1755128 (The Pile)

Max Activating Token Index: 119