Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 392 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.9768. Min Act: -0.0001

Data Index: 1371316 (Python Code)

Max Activating Token Index: 499

Text #1

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.9153. Min Act: -0.0001

Data Index: 1599084 (Python Code)

Max Activating Token Index: 914

Text #2

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8783. Min Act: -0.0001

Data Index: 1496423 (Python Code)

Max Activating Token Index: 454

Text #3

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7785. Min Act: -0.0000

Data Index: 192361 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7190. Min Act: -0.0001

Data Index: 1557953 (Python Code)

Max Activating Token Index: 155

Text #5

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7410. Min Act: -0.0001

Data Index: 1502983 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7312. Min Act: -0.0000

Data Index: 601162 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.5532. Min Act: -0.0001

Data Index: 1367553 (Python Code)

Max Activating Token Index: 542

Text #8

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6236. Min Act: -0.0000

Data Index: 282513 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6612. Min Act: -0.0001

Data Index: 1392116 (Python Code)

Max Activating Token Index: 977

Text #10

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6237. Min Act: -0.0001

Data Index: 1497670 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6484. Min Act: -0.0001

Data Index: 1570714 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6478. Min Act: -0.0001

Data Index: 1510079 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.5010. Min Act: -0.0001

Data Index: 1380611 (Python Code)

Max Activating Token Index: 716

Text #14

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6168. Min Act: -0.0001

Data Index: 1463922 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.5888. Min Act: -0.0001

Data Index: 1600055 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.5338. Min Act: -0.0001

Data Index: 1610883 (Python Code)

Max Activating Token Index: 975

Text #17

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.5875. Min Act: -0.0001

Data Index: 1612045 (Python Code)

Max Activating Token Index: 961

Text #18

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.5810. Min Act: -0.0001

Data Index: 1507327 (Python Code)

Max Activating Token Index: 704

Text #19

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6380. Min Act: -0.0001

Data Index: 824583 (C4 (Web Text))

Max Activating Token Index: 704