Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1490 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9398. Min Act: -0.0000

Data Index: 532240 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1250679 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9531. Min Act: -0.0000

Data Index: 1377119 (Python Code)

Max Activating Token Index: 90

Text #3

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8112. Min Act: -0.0000

Data Index: 771335 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8238. Min Act: -0.0000

Data Index: 315495 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1224472 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8094. Min Act: -0.0000

Data Index: 599369 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9016. Min Act: -0.0000

Data Index: 29364 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7796. Min Act: -0.0000

Data Index: 689341 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1656046 (Python Code)

Max Activating Token Index: 1005

Text #10

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1461225 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7242. Min Act: -0.0000

Data Index: 537739 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6784. Min Act: -0.0000

Data Index: 670032 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1440377 (Python Code)

Max Activating Token Index: 654

Text #14

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1534427 (Python Code)

Max Activating Token Index: 223

Text #15

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1221087 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1346299 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1289433 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.5646. Min Act: -0.0000

Data Index: 937303 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.5598. Min Act: -0.0000

Data Index: 980320 (C4 (Web Text))

Max Activating Token Index: 28