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

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

Neuron 2195 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1167378 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0569. Min Act: -0.0002

Data Index: 820696 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0550. Min Act: -0.0002

Data Index: 372518 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0568. Min Act: -0.0002

Data Index: 83103 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0559. Min Act: -0.0002

Data Index: 52713 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0574. Min Act: -0.0002

Data Index: 940892 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1276812 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0537. Min Act: -0.0002

Data Index: 745224 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0571. Min Act: -0.0002

Data Index: 675005 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0540. Min Act: -0.0002

Data Index: 16003 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0523. Min Act: -0.0002

Data Index: 988224 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0483. Min Act: -0.0002

Data Index: 313852 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0534. Min Act: -0.0002

Data Index: 951518 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1043923 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0551. Min Act: -0.0002

Data Index: 30653 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1224121 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0514. Min Act: -0.0002

Data Index: 766267 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0550. Min Act: -0.0002

Data Index: 215054 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0524. Min Act: -0.0002

Data Index: 269004 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0555. Min Act: -0.0002

Data Index: 91803 (C4 (Web Text))

Max Activating Token Index: 288