Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 766 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0548. Min Act: -0.0006

Data Index: 1246504 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0006

Data Index: 1002990 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0553. Min Act: -0.0006

Data Index: 910327 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0497. Min Act: -0.0006

Data Index: 44305 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0508. Min Act: -0.0006

Data Index: 1146100 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0493. Min Act: -0.0006

Data Index: 87730 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0464. Min Act: -0.0006

Data Index: 49214 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0460. Min Act: -0.0006

Data Index: 787268 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0483. Min Act: -0.0006

Data Index: 333906 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0479. Min Act: -0.0006

Data Index: 347117 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0456. Min Act: -0.0006

Data Index: 391111 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0463. Min Act: -0.0006

Data Index: 654305 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0444. Min Act: -0.0006

Data Index: 933611 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0462. Min Act: -0.0006

Data Index: 381600 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0447. Min Act: -0.0006

Data Index: 946375 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0446. Min Act: -0.0006

Data Index: 731340 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0446. Min Act: -0.0006

Data Index: 587981 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0408. Min Act: -0.0006

Data Index: 1159908 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0445. Min Act: -0.0006

Data Index: 968993 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0427. Min Act: -0.0006

Data Index: 561441 (C4 (Web Text))

Max Activating Token Index: 67