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

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

Neuron 5639 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.8546. Min Act: 0.0000

Data Index: 759864 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.8213. Min Act: -0.0000

Data Index: 590739 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7547. Min Act: -0.0000

Data Index: 234664 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7547. Min Act: 0.0001

Data Index: 112629 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7734. Min Act: -0.0000

Data Index: 319389 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1187678 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7331. Min Act: -0.0000

Data Index: 856778 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7265. Min Act: -0.0000

Data Index: 209574 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7878. Min Act: -0.0000

Data Index: 167661 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7419. Min Act: -0.0000

Data Index: 754830 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7462. Min Act: -0.0000

Data Index: 759837 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7117. Min Act: -0.0000

Data Index: 260711 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6692. Min Act: 0.0000

Data Index: 701557 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6859. Min Act: -0.0000

Data Index: 368331 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6402. Min Act: -0.0000

Data Index: 46475 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1279136 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6452. Min Act: -0.0000

Data Index: 669169 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1134072 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7019. Min Act: -0.0000

Data Index: 78951 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6229. Min Act: -0.0000

Data Index: 845420 (C4 (Web Text))

Max Activating Token Index: 821