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

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

Neuron 2439 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: 0.8822. Min Range: -0.8822

Max Act: 0.8822. Min Act: -0.0001

Data Index: 615666 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.8108. Min Act: -0.0002

Data Index: 864735 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.8559. Min Act: -0.0002

Data Index: 659968 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.8463. Min Act: -0.0002

Data Index: 781836 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.8644. Min Act: -0.0002

Data Index: 827356 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7812. Min Act: -0.0001

Data Index: 975942 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.8257. Min Act: -0.0002

Data Index: 42695 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7940. Min Act: -0.0001

Data Index: 167010 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7747. Min Act: -0.0002

Data Index: 764128 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.8394. Min Act: -0.0001

Data Index: 631547 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7762. Min Act: -0.0001

Data Index: 223754 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7745. Min Act: -0.0002

Data Index: 636937 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7933. Min Act: -0.0002

Data Index: 598918 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7907. Min Act: -0.0002

Data Index: 945261 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7423. Min Act: -0.0002

Data Index: 1211792 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7974. Min Act: -0.0002

Data Index: 1219853 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.6735. Min Act: -0.0002

Data Index: 290816 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7816. Min Act: -0.0002

Data Index: 254730 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.7529. Min Act: -0.0001

Data Index: 1035848 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.8822. Min Range: -0.8822

Max Act: 0.8242. Min Act: -0.0002

Data Index: 178848 (C4 (Web Text))

Max Activating Token Index: 771