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

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

Neuron 1413 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.9010. Min Act: 0.0000

Data Index: 626493 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7260. Min Act: -0.0000

Data Index: 10584 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7193. Min Act: 0.0000

Data Index: 1032879 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1502175 (Python Code)

Max Activating Token Index: 971

Text #4

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1484048 (Python Code)

Max Activating Token Index: 190

Text #5

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1362989 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6752. Min Act: 0.0000

Data Index: 218514 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1094111 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6743. Min Act: -0.0000

Data Index: 27849 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1581503 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1509368 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1545469 (Python Code)

Max Activating Token Index: 350

Text #12

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5575. Min Act: -0.0000

Data Index: 620201 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6348. Min Act: 0.0000

Data Index: 846550 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6296. Min Act: -0.0000

Data Index: 347587 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5890. Min Act: -0.0000

Data Index: 867455 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6229. Min Act: -0.0000

Data Index: 914370 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6115. Min Act: 0.0000

Data Index: 173290 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1609286 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6106. Min Act: 0.0000

Data Index: 1157294 (C4 (Web Text))

Max Activating Token Index: 452