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

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

Neuron 3648 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.8353. Min Act: -0.0000

Data Index: 1625766 (Python Code)

Max Activating Token Index: 720

Text #1

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.5458. Min Act: -0.0000

Data Index: 1467367 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.7981. Min Act: -0.0000

Data Index: 1425370 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.6464. Min Act: -0.0000

Data Index: 1515750 (Python Code)

Max Activating Token Index: 464

Text #4

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.2114. Min Act: -0.0000

Data Index: 1551052 (Python Code)

Max Activating Token Index: 404

Text #5

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.5127. Min Act: -0.0000

Data Index: 1637134 (Python Code)

Max Activating Token Index: 234

Text #6

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.2636. Min Act: -0.0000

Data Index: 1366731 (Python Code)

Max Activating Token Index: 464

Text #7

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.4115. Min Act: -0.0000

Data Index: 1458308 (Python Code)

Max Activating Token Index: 160

Text #8

Max Range: 3.8353. Min Range: -3.8353

Max Act: 2.9315. Min Act: -0.0000

Data Index: 1530883 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.1975. Min Act: -0.0000

Data Index: 1504804 (Python Code)

Max Activating Token Index: 375

Text #10

Max Range: 3.8353. Min Range: -3.8353

Max Act: 2.8862. Min Act: -0.0000

Data Index: 1509029 (Python Code)

Max Activating Token Index: 768

Text #11

Max Range: 3.8353. Min Range: -3.8353

Max Act: 2.9952. Min Act: -0.0000

Data Index: 1549127 (Python Code)

Max Activating Token Index: 660

Text #12

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.1339. Min Act: -0.0000

Data Index: 1438573 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.0421. Min Act: -0.0000

Data Index: 1644612 (Python Code)

Max Activating Token Index: 779

Text #14

Max Range: 3.8353. Min Range: -3.8353

Max Act: 2.9285. Min Act: -0.0000

Data Index: 1462168 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.0164. Min Act: -0.0000

Data Index: 1602360 (Python Code)

Max Activating Token Index: 758

Text #16

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.0313. Min Act: -0.0000

Data Index: 1549063 (Python Code)

Max Activating Token Index: 492

Text #17

Max Range: 3.8353. Min Range: -3.8353

Max Act: 2.8854. Min Act: -0.0000

Data Index: 1487710 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 3.8353. Min Range: -3.8353

Max Act: 3.1507. Min Act: -0.0000

Data Index: 1642273 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 3.8353. Min Range: -3.8353

Max Act: 2.9521. Min Act: -0.0000

Data Index: 1621611 (Python Code)

Max Activating Token Index: 846