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

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

Neuron 593 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6873. Min Act: -0.0000

Data Index: 1543835 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1481641 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1405624 (Python Code)

Max Activating Token Index: 657

Text #3

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1649366 (Python Code)

Max Activating Token Index: 759

Text #4

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1396742 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5663. Min Act: 0.0000

Data Index: 1492233 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5454. Min Act: 0.0000

Data Index: 1581234 (Python Code)

Max Activating Token Index: 502

Text #7

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5420. Min Act: 0.0000

Data Index: 1457316 (Python Code)

Max Activating Token Index: 531

Text #8

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4956. Min Act: 0.0001

Data Index: 1410350 (Python Code)

Max Activating Token Index: 739

Text #9

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5374. Min Act: 0.0000

Data Index: 1633482 (Python Code)

Max Activating Token Index: 280

Text #10

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5538. Min Act: -0.0000

Data Index: 397664 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1452566 (Python Code)

Max Activating Token Index: 982

Text #12

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5617. Min Act: 0.0000

Data Index: 1389146 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1468279 (Python Code)

Max Activating Token Index: 589

Text #14

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1602936 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1473871 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5141. Min Act: -0.0000

Data Index: 587557 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1616306 (Python Code)

Max Activating Token Index: 881

Text #18

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1504863 (Python Code)

Max Activating Token Index: 549

Text #19

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1519781 (Python Code)

Max Activating Token Index: 415