Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2595 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.9513. Min Act: -0.0000

Data Index: 714360 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.7595. Min Act: -0.0000

Data Index: 1557307 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.8284. Min Act: -0.0000

Data Index: 1686598 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.4453. Min Act: -0.0000

Data Index: 1311616 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.5461. Min Act: -0.0000

Data Index: 396372 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.4002. Min Act: -0.0000

Data Index: 1313443 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.6591. Min Act: -0.0000

Data Index: 1772437 (The Pile)

Max Activating Token Index: 852

Text #7

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.4800. Min Act: -0.0000

Data Index: 524119 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.1353. Min Act: -0.0000

Data Index: 566645 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.1800. Min Act: -0.0000

Data Index: 1849095 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.1864. Min Act: -0.0000

Data Index: 1644654 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.1316. Min Act: -0.0000

Data Index: 572243 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.1053. Min Act: -0.0000

Data Index: 1169861 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.9514. Min Act: -0.0000

Data Index: 1584554 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.0725. Min Act: -0.0000

Data Index: 972169 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.0750. Min Act: -0.0000

Data Index: 1922604 (The Pile)

Max Activating Token Index: 894

Text #16

Max Range: 3.9513. Min Range: -3.9513

Max Act: 3.2370. Min Act: 0.0000

Data Index: 360650 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.9296. Min Act: 0.0000

Data Index: 1973730 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.9072. Min Act: 0.0000

Data Index: 599033 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 3.9513. Min Range: -3.9513

Max Act: 2.9853. Min Act: -0.0000

Data Index: 688930 (The Pile)

Max Activating Token Index: 605