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

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

Neuron 5570 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3621. Min Act: -0.0001

Data Index: 1617190 (Python Code)

Max Activating Token Index: 766

Text #1

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.2019. Min Act: -0.0000

Data Index: 1374199 (Python Code)

Max Activating Token Index: 622

Text #2

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.5517. Min Act: -0.0001

Data Index: 1644335 (Python Code)

Max Activating Token Index: 207

Text #3

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.1000. Min Act: -0.0001

Data Index: 1455369 (Python Code)

Max Activating Token Index: 687

Text #4

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.8174. Min Act: -0.0000

Data Index: 1637911 (Python Code)

Max Activating Token Index: 338

Text #5

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.6535. Min Act: -0.0001

Data Index: 1392331 (Python Code)

Max Activating Token Index: 835

Text #6

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.8710. Min Act: -0.0000

Data Index: 1442748 (Python Code)

Max Activating Token Index: 748

Text #7

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.6209. Min Act: -0.0001

Data Index: 1477607 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.4784. Min Act: -0.0001

Data Index: 1381658 (Python Code)

Max Activating Token Index: 506

Text #9

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.5908. Min Act: -0.0001

Data Index: 1496385 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.6894. Min Act: -0.0000

Data Index: 1538513 (Python Code)

Max Activating Token Index: 72

Text #11

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.6734. Min Act: -0.0001

Data Index: 1458104 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.4852. Min Act: -0.0001

Data Index: 1646057 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.6111. Min Act: -0.0001

Data Index: 1469567 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.3627. Min Act: -0.0000

Data Index: 1395922 (Python Code)

Max Activating Token Index: 266

Text #15

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.2236. Min Act: -0.0001

Data Index: 1526641 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.4843. Min Act: -0.0000

Data Index: 1578930 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.4487. Min Act: -0.0001

Data Index: 1593618 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.3361. Min Act: -0.0001

Data Index: 1395948 (Python Code)

Max Activating Token Index: 212

Text #19

Max Range: 3.5517. Min Range: -3.5517

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1574008 (Python Code)

Max Activating Token Index: 354