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

Dataset: The Pile

Neuron 2777 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8883. Min Act: -0.0000

Data Index: 510561 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8563. Min Act: -0.0000

Data Index: 203499 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7820. Min Act: -0.0000

Data Index: 671463 (The Pile)

Max Activating Token Index: 961

Text #3

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1173780 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7779. Min Act: -0.0000

Data Index: 151628 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1307072 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7541. Min Act: 0.0000

Data Index: 347548 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1928569 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7758. Min Act: 0.0000

Data Index: 1378461 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1922035 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7398. Min Act: -0.0000

Data Index: 799925 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7726. Min Act: 0.0000

Data Index: 1800640 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.5763. Min Act: -0.0000

Data Index: 277741 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6909. Min Act: -0.0000

Data Index: 773259 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1920340 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6446. Min Act: -0.0000

Data Index: 610026 (The Pile)

Max Activating Token Index: 178

Text #16

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6684. Min Act: 0.0000

Data Index: 1573397 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6570. Min Act: -0.0000

Data Index: 794635 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1186129 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.5673. Min Act: 0.0000

Data Index: 933973 (The Pile)

Max Activating Token Index: 966