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

Dataset: The Pile

Neuron 3791 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: 3.4413. Min Range: -3.4413

Max Act: 3.4348. Min Act: -0.0000

Data Index: 391031 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 3.4413. Min Range: -3.4413

Max Act: 3.4413. Min Act: -0.0000

Data Index: 372717 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.2504. Min Act: -0.0000

Data Index: 1864736 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 3.4413. Min Range: -3.4413

Max Act: 3.0719. Min Act: -0.0000

Data Index: 1873505 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 3.4413. Min Range: -3.4413

Max Act: 3.2420. Min Act: -0.0000

Data Index: 48044 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.6332. Min Act: -0.0000

Data Index: 129536 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.2100. Min Act: -0.0000

Data Index: 170722 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.5549. Min Act: -0.0000

Data Index: 121294 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.1940. Min Act: -0.0000

Data Index: 932555 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.5696. Min Act: -0.0000

Data Index: 1217956 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.2786. Min Act: -0.0000

Data Index: 1562859 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.3371. Min Act: -0.0000

Data Index: 561699 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.1341. Min Act: -0.0000

Data Index: 765177 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 3.4413. Min Range: -3.4413

Max Act: 1.9064. Min Act: -0.0000

Data Index: 77335 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.2771. Min Act: -0.0000

Data Index: 495587 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.5275. Min Act: -0.0000

Data Index: 139632 (The Pile)

Max Activating Token Index: 785

Text #16

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.2261. Min Act: -0.0000

Data Index: 649876 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.1806. Min Act: -0.0000

Data Index: 1154417 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 3.4413. Min Range: -3.4413

Max Act: 2.2041. Min Act: -0.0000

Data Index: 69161 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 3.4413. Min Range: -3.4413

Max Act: 1.7475. Min Act: -0.0000

Data Index: 1130812 (The Pile)

Max Activating Token Index: 738