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

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

Neuron 5993 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1492919 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3587. Min Act: -0.0000

Data Index: 594643 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2513. Min Act: -0.0001

Data Index: 930332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1291343 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2382. Min Act: -0.0001

Data Index: 216325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2888. Min Act: -0.0001

Data Index: 1645343 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1653444 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2313. Min Act: -0.0000

Data Index: 878077 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1533627 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1599665 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2107. Min Act: -0.0000

Data Index: 250950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1240085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2089. Min Act: -0.0001

Data Index: 105401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.0922. Min Act: -0.0001

Data Index: 632666 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.1913. Min Act: -0.0001

Data Index: 392150 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2020. Min Act: -0.0001

Data Index: 1613607 (Python Code)

Max Activating Token Index: 974

Text #16

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1652863 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.1492. Min Act: -0.0001

Data Index: 1242255 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1532958 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.1728. Min Act: -0.0001

Data Index: 72395 (C4 (Web Text))

Max Activating Token Index: 1023