Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2427 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0001

Data Index: 1315357 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1200964 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0535. Min Act: -0.0001

Data Index: 805718 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1625750 (Python Code)

Max Activating Token Index: 786

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1541240 (Python Code)

Max Activating Token Index: 1005

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0469. Min Act: -0.0001

Data Index: 661872 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1620323 (Python Code)

Max Activating Token Index: 843

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0454. Min Act: -0.0001

Data Index: 306750 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1438464 (Python Code)

Max Activating Token Index: 201

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0447. Min Act: -0.0001

Data Index: 470872 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0411. Min Act: -0.0001

Data Index: 534675 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0417. Min Act: -0.0001

Data Index: 123977 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0422. Min Act: -0.0001

Data Index: 225918 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0404. Min Act: -0.0001

Data Index: 641639 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0389. Min Act: -0.0001

Data Index: 464249 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0360. Min Act: -0.0001

Data Index: 7935 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0380. Min Act: -0.0001

Data Index: 947806 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1377432 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1538851 (Python Code)

Max Activating Token Index: 891

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0419. Min Act: -0.0001

Data Index: 596127 (C4 (Web Text))

Max Activating Token Index: 729