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

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

Neuron 927 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1379012 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1401224 (Python Code)

Max Activating Token Index: 494

Text #2

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1649079 (Python Code)

Max Activating Token Index: 699

Text #3

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1475790 (Python Code)

Max Activating Token Index: 905

Text #4

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9683. Min Act: -0.0000

Data Index: 715233 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8949. Min Act: 0.0000

Data Index: 1645466 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8609. Min Act: -0.0000

Data Index: 112147 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1391511 (Python Code)

Max Activating Token Index: 722

Text #8

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1554401 (Python Code)

Max Activating Token Index: 353

Text #9

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1525706 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8973. Min Act: 0.0000

Data Index: 1572971 (Python Code)

Max Activating Token Index: 118

Text #11

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1557011 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8260. Min Act: -0.0000

Data Index: 535720 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1429388 (Python Code)

Max Activating Token Index: 496

Text #14

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8223. Min Act: -0.0000

Data Index: 791378 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1540190 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.7857. Min Act: 0.0000

Data Index: 1534472 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8201. Min Act: -0.0000

Data Index: 848290 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.7876. Min Act: -0.0000

Data Index: 412669 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.7683. Min Act: -0.0000

Data Index: 980090 (C4 (Web Text))

Max Activating Token Index: 84