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

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

Neuron 4875 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1095830 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1554681 (Python Code)

Max Activating Token Index: 459

Text #2

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3633. Min Act: -0.0000

Data Index: 1416582 (Python Code)

Max Activating Token Index: 517

Text #3

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1606394 (Python Code)

Max Activating Token Index: 568

Text #4

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1583696 (Python Code)

Max Activating Token Index: 719

Text #5

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1477259 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.4169. Min Act: -0.0000

Data Index: 1653722 (Python Code)

Max Activating Token Index: 444

Text #7

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3707. Min Act: -0.0000

Data Index: 115400 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3360. Min Act: -0.0000

Data Index: 1464384 (Python Code)

Max Activating Token Index: 291

Text #9

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1374849 (Python Code)

Max Activating Token Index: 166

Text #10

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3476. Min Act: -0.0000

Data Index: 1458080 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1621503 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3527. Min Act: -0.0000

Data Index: 1626864 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1535088 (Python Code)

Max Activating Token Index: 507

Text #14

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2600. Min Act: -0.0000

Data Index: 1541989 (Python Code)

Max Activating Token Index: 689

Text #15

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3798. Min Act: -0.0000

Data Index: 1381780 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.4174. Min Act: -0.0000

Data Index: 593923 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1521119 (Python Code)

Max Activating Token Index: 504

Text #18

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3611. Min Act: -0.0000

Data Index: 222811 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1655571 (Python Code)

Max Activating Token Index: 460