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

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

Neuron 1768 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1085817 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.4896. Min Act: -0.0000

Data Index: 447856 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.4333. Min Act: -0.0000

Data Index: 984775 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.4182. Min Act: -0.0000

Data Index: 753248 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.4316. Min Act: -0.0001

Data Index: 216472 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3985. Min Act: -0.0000

Data Index: 981815 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3720. Min Act: -0.0001

Data Index: 1008903 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3645. Min Act: -0.0001

Data Index: 77872 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3766. Min Act: -0.0001

Data Index: 507308 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3601. Min Act: -0.0000

Data Index: 208150 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3772. Min Act: -0.0000

Data Index: 833888 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3561. Min Act: -0.0000

Data Index: 853950 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1343334 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3557. Min Act: -0.0000

Data Index: 328142 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3413. Min Act: -0.0001

Data Index: 1037221 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3394. Min Act: -0.0000

Data Index: 357840 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3398. Min Act: -0.0001

Data Index: 1003401 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3238. Min Act: -0.0000

Data Index: 961921 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3099. Min Act: -0.0001

Data Index: 1049403 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.5051. Min Range: -0.5051

Max Act: 0.3470. Min Act: -0.0001

Data Index: 850463 (C4 (Web Text))

Max Activating Token Index: 44