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

Dataset: The Pile

Neuron 1705 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: 0.7482. Min Range: -0.7482

Max Act: 0.7203. Min Act: -0.0000

Data Index: 20909 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1477711 (The Pile)

Max Activating Token Index: 516

Text #2

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.7354. Min Act: -0.0000

Data Index: 625525 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1373170 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1426118 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6798. Min Act: -0.0000

Data Index: 922738 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1672292 (The Pile)

Max Activating Token Index: 804

Text #7

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1456366 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1494775 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1617063 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1259368 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.7212. Min Act: -0.0000

Data Index: 632178 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1727571 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6522. Min Act: -0.0000

Data Index: 435980 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6920. Min Act: -0.0000

Data Index: 711930 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1281327 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6274. Min Act: -0.0000

Data Index: 55952 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6458. Min Act: -0.0000

Data Index: 889514 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1900303 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1452083 (The Pile)

Max Activating Token Index: 319