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

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

Neuron 3114 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1645607 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0116. Min Act: -0.0001

Data Index: 1344640 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1611075 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9574. Min Act: -0.0000

Data Index: 930016 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0047. Min Act: -0.0001

Data Index: 44509 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1204558 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9729. Min Act: -0.0000

Data Index: 353485 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9406. Min Act: -0.0001

Data Index: 1052122 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9406. Min Act: -0.0000

Data Index: 535842 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1062411 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9406. Min Act: -0.0000

Data Index: 872464 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9406. Min Act: -0.0000

Data Index: 560118 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9033. Min Act: -0.0000

Data Index: 391321 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9267. Min Act: -0.0000

Data Index: 63536 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1397705 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8479. Min Act: -0.0000

Data Index: 923525 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1385297 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8618. Min Act: -0.0000

Data Index: 555040 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8815. Min Act: -0.0000

Data Index: 630210 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8131. Min Act: -0.0000

Data Index: 992274 (C4 (Web Text))

Max Activating Token Index: 574