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

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

Neuron 5928 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6287. Min Range: -3.6287

Max Act: 3.6287. Min Act: -0.0000

Data Index: 1433607 (Python Code)

Max Activating Token Index: 407

Text #1

Max Range: 3.6287. Min Range: -3.6287

Max Act: 3.2022. Min Act: -0.0000

Data Index: 1612187 (Python Code)

Max Activating Token Index: 432

Text #2

Max Range: 3.6287. Min Range: -3.6287

Max Act: 3.1708. Min Act: -0.0000

Data Index: 1426659 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.8819. Min Act: -0.0000

Data Index: 1399621 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.7206. Min Act: -0.0000

Data Index: 1481905 (Python Code)

Max Activating Token Index: 675

Text #5

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.7608. Min Act: -0.0000

Data Index: 1465595 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.4761. Min Act: -0.0000

Data Index: 1602189 (Python Code)

Max Activating Token Index: 839

Text #7

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.3021. Min Act: -0.0000

Data Index: 1414397 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.3755. Min Act: -0.0000

Data Index: 1476064 (Python Code)

Max Activating Token Index: 238

Text #9

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.2015. Min Act: -0.0000

Data Index: 1618955 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.1690. Min Act: -0.0000

Data Index: 1570041 (Python Code)

Max Activating Token Index: 257

Text #11

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.0283. Min Act: -0.0000

Data Index: 1518037 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.1427. Min Act: -0.0000

Data Index: 1394593 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.0604. Min Act: -0.0000

Data Index: 1581051 (Python Code)

Max Activating Token Index: 393

Text #14

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.1680. Min Act: -0.0000

Data Index: 1623529 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.1582. Min Act: -0.0000

Data Index: 1501168 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 3.6287. Min Range: -3.6287

Max Act: 2.1963. Min Act: -0.0000

Data Index: 1387411 (Python Code)

Max Activating Token Index: 967

Text #17

Max Range: 3.6287. Min Range: -3.6287

Max Act: 1.9302. Min Act: -0.0000

Data Index: 1461066 (Python Code)

Max Activating Token Index: 44

Text #18

Max Range: 3.6287. Min Range: -3.6287

Max Act: 1.9573. Min Act: -0.0000

Data Index: 1460570 (Python Code)

Max Activating Token Index: 356

Text #19

Max Range: 3.6287. Min Range: -3.6287

Max Act: 1.9053. Min Act: -0.0000

Data Index: 1531700 (Python Code)

Max Activating Token Index: 21