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

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

Neuron 5668 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0721. Min Range: -1.0721

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1152587 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.9991. Min Act: -0.0000

Data Index: 874017 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.9977. Min Act: -0.0000

Data Index: 14703 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.9641. Min Act: -0.0000

Data Index: 769485 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8727. Min Act: -0.0000

Data Index: 757112 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1300914 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.9122. Min Act: -0.0000

Data Index: 920062 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8746. Min Act: -0.0000

Data Index: 544173 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1531914 (Python Code)

Max Activating Token Index: 355

Text #9

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1054468 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1528399 (Python Code)

Max Activating Token Index: 915

Text #11

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1556397 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1653338 (Python Code)

Max Activating Token Index: 605

Text #13

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1153341 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1327208 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1545064 (Python Code)

Max Activating Token Index: 507

Text #16

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1623712 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1541942 (Python Code)

Max Activating Token Index: 181

Text #18

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1540006 (Python Code)

Max Activating Token Index: 953

Text #19

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8238. Min Act: -0.0000

Data Index: 183254 (C4 (Web Text))

Max Activating Token Index: 504