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

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

Neuron 3034 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2872. Min Act: -0.0002

Data Index: 1059795 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1703. Min Act: -0.0002

Data Index: 275365 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1295083 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1400857 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1038314 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0433. Min Act: -0.0001

Data Index: 406700 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0390. Min Act: -0.0002

Data Index: 120527 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1462151 (Python Code)

Max Activating Token Index: 457

Text #8

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0366. Min Act: -0.0001

Data Index: 650854 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0391. Min Act: -0.0001

Data Index: 429532 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1563341 (Python Code)

Max Activating Token Index: 143

Text #11

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1358117 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0359. Min Act: -0.0001

Data Index: 272537 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0348. Min Act: -0.0001

Data Index: 906927 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1592608 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0316. Min Act: -0.0002

Data Index: 4994 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1369994 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0317. Min Act: -0.0001

Data Index: 812029 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0314. Min Act: -0.0002

Data Index: 478018 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.0310. Min Act: -0.0001

Data Index: 879442 (C4 (Web Text))

Max Activating Token Index: 338