Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 519 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0429. Min Range: -1.0429

Max Act: 1.0429. Min Act: -0.0001

Data Index: 1510850 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9878. Min Act: -0.0001

Data Index: 1489269 (Python Code)

Max Activating Token Index: 112

Text #2

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9828. Min Act: -0.0001

Data Index: 1559683 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1653807 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9803. Min Act: -0.0001

Data Index: 1465386 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8901. Min Act: -0.0001

Data Index: 1395884 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9363. Min Act: -0.0001

Data Index: 1520156 (Python Code)

Max Activating Token Index: 723

Text #7

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8955. Min Act: -0.0001

Data Index: 1617920 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8340. Min Act: -0.0001

Data Index: 1411877 (Python Code)

Max Activating Token Index: 862

Text #9

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8349. Min Act: -0.0001

Data Index: 1654524 (Python Code)

Max Activating Token Index: 489

Text #10

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8540. Min Act: -0.0001

Data Index: 1639297 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7907. Min Act: -0.0001

Data Index: 1553959 (Python Code)

Max Activating Token Index: 824

Text #12

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8319. Min Act: -0.0001

Data Index: 1433068 (Python Code)

Max Activating Token Index: 696

Text #13

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8031. Min Act: -0.0001

Data Index: 1630444 (Python Code)

Max Activating Token Index: 676

Text #14

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8099. Min Act: -0.0001

Data Index: 1508458 (Python Code)

Max Activating Token Index: 228

Text #15

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8790. Min Act: -0.0001

Data Index: 1552903 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7969. Min Act: -0.0001

Data Index: 1394539 (Python Code)

Max Activating Token Index: 971

Text #17

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7425. Min Act: -0.0001

Data Index: 1439661 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7850. Min Act: -0.0001

Data Index: 1455685 (Python Code)

Max Activating Token Index: 509

Text #19

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1465310 (Python Code)

Max Activating Token Index: 126