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

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

Neuron 4403 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0198. Min Range: -2.0198

Max Act: 2.0103. Min Act: -0.0000

Data Index: 787709 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 2.0198. Min Range: -2.0198

Max Act: 2.0198. Min Act: -0.0000

Data Index: 440570 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.7375. Min Act: -0.0000

Data Index: 351024 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.7522. Min Act: -0.0000

Data Index: 645671 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.6786. Min Act: -0.0000

Data Index: 298330 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.7790. Min Act: -0.0000

Data Index: 754035 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.8654. Min Act: -0.0000

Data Index: 710879 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.6928. Min Act: -0.0000

Data Index: 705226 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.6071. Min Act: -0.0000

Data Index: 440820 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.6939. Min Act: -0.0000

Data Index: 973798 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1070229 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.6744. Min Act: -0.0000

Data Index: 852449 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.5889. Min Act: -0.0000

Data Index: 212685 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.4859. Min Act: -0.0000

Data Index: 611767 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.5873. Min Act: -0.0000

Data Index: 1067836 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.5350. Min Act: -0.0000

Data Index: 280731 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.5282. Min Act: -0.0000

Data Index: 836370 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.4482. Min Act: -0.0000

Data Index: 389984 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.4968. Min Act: -0.0000

Data Index: 431934 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 2.0198. Min Range: -2.0198

Max Act: 1.4908. Min Act: -0.0000

Data Index: 195429 (C4 (Web Text))

Max Activating Token Index: 577