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

Dataset: The Pile

Neuron 2050 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0372. Min Range: -1.0372

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1046231 (The Pile)

Max Activating Token Index: 931

Text #1

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8388. Min Act: -0.0000

Data Index: 294165 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8080. Min Act: -0.0000

Data Index: 135000 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1546870 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7576. Min Act: -0.0000

Data Index: 645262 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1141743 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1785950 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1805232 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7236. Min Act: -0.0000

Data Index: 821171 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7163. Min Act: -0.0000

Data Index: 430093 (The Pile)

Max Activating Token Index: 29

Text #10

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1485128 (The Pile)

Max Activating Token Index: 890

Text #11

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1818007 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1930204 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6634. Min Act: -0.0000

Data Index: 955024 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1577956 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1800586 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6844. Min Act: -0.0000

Data Index: 545551 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1775363 (The Pile)

Max Activating Token Index: 690

Text #18

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6315. Min Act: -0.0000

Data Index: 443827 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6253. Min Act: -0.0000

Data Index: 452258 (The Pile)

Max Activating Token Index: 49