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

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

Neuron 1655 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1355087 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1834. Min Act: -0.0000

Data Index: 801861 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1798. Min Act: -0.0000

Data Index: 593787 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1707. Min Act: -0.0000

Data Index: 451583 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1657. Min Act: -0.0000

Data Index: 393364 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1761. Min Act: -0.0000

Data Index: 846265 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1581. Min Act: -0.0000

Data Index: 957754 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1612. Min Act: -0.0000

Data Index: 317225 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1049649 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1398. Min Act: -0.0000

Data Index: 876667 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1383. Min Act: -0.0000

Data Index: 168096 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1442. Min Act: -0.0000

Data Index: 117036 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1357. Min Act: -0.0000

Data Index: 973002 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1396. Min Act: -0.0000

Data Index: 803742 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1342. Min Act: -0.0000

Data Index: 691374 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1406. Min Act: -0.0000

Data Index: 162434 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1037912 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1071675 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1364. Min Act: -0.0000

Data Index: 757416 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1373. Min Act: -0.0000

Data Index: 928311 (C4 (Web Text))

Max Activating Token Index: 691