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

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

Neuron 499 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.6265. Min Act: -0.0000

Data Index: 1430230 (Python Code)

Max Activating Token Index: 294

Text #1

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.7266. Min Act: -0.0000

Data Index: 1418293 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.3507. Min Act: -0.0000

Data Index: 1365832 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.2647. Min Act: -0.0000

Data Index: 1443273 (Python Code)

Max Activating Token Index: 433

Text #4

Max Range: 4.7266. Min Range: -4.7266

Max Act: 3.9869. Min Act: -0.0000

Data Index: 1588195 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4634. Min Act: -0.0000

Data Index: 1370196 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.1083. Min Act: -0.0000

Data Index: 1548676 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.3956. Min Act: -0.0000

Data Index: 1566399 (Python Code)

Max Activating Token Index: 278

Text #8

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.0580. Min Act: -0.0000

Data Index: 1561149 (Python Code)

Max Activating Token Index: 462

Text #9

Max Range: 4.7266. Min Range: -4.7266

Max Act: 3.9642. Min Act: -0.0000

Data Index: 1536760 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.1124. Min Act: -0.0000

Data Index: 1633710 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 4.7266. Min Range: -4.7266

Max Act: 3.9504. Min Act: -0.0000

Data Index: 1582632 (Python Code)

Max Activating Token Index: 762

Text #12

Max Range: 4.7266. Min Range: -4.7266

Max Act: 3.7508. Min Act: -0.0000

Data Index: 1583020 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 4.7266. Min Range: -4.7266

Max Act: 3.9061. Min Act: -0.0000

Data Index: 1390088 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.0302. Min Act: -0.0000

Data Index: 1514156 (Python Code)

Max Activating Token Index: 419

Text #15

Max Range: 4.7266. Min Range: -4.7266

Max Act: 3.7888. Min Act: -0.0000

Data Index: 1648161 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.1324. Min Act: -0.0000

Data Index: 1464947 (Python Code)

Max Activating Token Index: 818

Text #17

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.1022. Min Act: -0.0000

Data Index: 1498884 (Python Code)

Max Activating Token Index: 695

Text #18

Max Range: 4.7266. Min Range: -4.7266

Max Act: 3.9197. Min Act: -0.0000

Data Index: 1617371 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.0828. Min Act: -0.0000

Data Index: 1569668 (Python Code)

Max Activating Token Index: 10