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

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

Neuron 5308 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1458673 (Python Code)

Max Activating Token Index: 315

Text #1

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1610741 (Python Code)

Max Activating Token Index: 131

Text #2

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1581452 (Python Code)

Max Activating Token Index: 344

Text #3

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1373795 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1501301 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1447868 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1480547 (Python Code)

Max Activating Token Index: 584

Text #7

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1574031 (Python Code)

Max Activating Token Index: 668

Text #8

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1429496 (Python Code)

Max Activating Token Index: 723

Text #9

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1478502 (Python Code)

Max Activating Token Index: 434

Text #10

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1432135 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1531556 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1509075 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1387075 (Python Code)

Max Activating Token Index: 230

Text #14

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1634170 (Python Code)

Max Activating Token Index: 616

Text #15

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1428312 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1517255 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1613434 (Python Code)

Max Activating Token Index: 990

Text #18

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1632942 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1427892 (Python Code)

Max Activating Token Index: 767