Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4514 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1679. Min Range: -2.1679

Max Act: 2.1679. Min Act: -0.0000

Data Index: 881527 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.8487. Min Act: -0.0000

Data Index: 1285375 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.7237. Min Act: -0.0000

Data Index: 1019403 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.8144. Min Act: -0.0000

Data Index: 931649 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.6989. Min Act: -0.0000

Data Index: 961337 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.8784. Min Act: -0.0000

Data Index: 535335 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.7553. Min Act: -0.0000

Data Index: 170633 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.7175. Min Act: -0.0000

Data Index: 285446 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.6363. Min Act: -0.0000

Data Index: 71123 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.6395. Min Act: -0.0000

Data Index: 582923 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1326685 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.5596. Min Act: -0.0000

Data Index: 809400 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.6227. Min Act: -0.0000

Data Index: 651459 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.5495. Min Act: -0.0000

Data Index: 977022 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.5399. Min Act: -0.0000

Data Index: 863815 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.5339. Min Act: -0.0000

Data Index: 124047 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.5375. Min Act: -0.0000

Data Index: 1190457 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.5255. Min Act: -0.0000

Data Index: 718604 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.5087. Min Act: -0.0000

Data Index: 744489 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 2.1679. Min Range: -2.1679

Max Act: 1.5123. Min Act: -0.0000

Data Index: 459967 (C4 (Web Text))

Max Activating Token Index: 932