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

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

Neuron 5706 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1120. Min Range: -2.1120

Max Act: 2.1120. Min Act: -0.0000

Data Index: 1650914 (Python Code)

Max Activating Token Index: 833

Text #1

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.7867. Min Act: -0.0000

Data Index: 1503308 (Python Code)

Max Activating Token Index: 673

Text #2

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.5483. Min Act: -0.0000

Data Index: 1533102 (Python Code)

Max Activating Token Index: 210

Text #3

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.6995. Min Act: -0.0000

Data Index: 1459588 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.7757. Min Act: -0.0000

Data Index: 1510705 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.4083. Min Act: -0.0000

Data Index: 1596812 (Python Code)

Max Activating Token Index: 382

Text #6

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.5712. Min Act: -0.0000

Data Index: 1369367 (Python Code)

Max Activating Token Index: 474

Text #7

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.4165. Min Act: -0.0000

Data Index: 1523498 (Python Code)

Max Activating Token Index: 433

Text #8

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1638919 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1524721 (Python Code)

Max Activating Token Index: 693

Text #10

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1547213 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.2793. Min Act: -0.0000

Data Index: 1652182 (Python Code)

Max Activating Token Index: 190

Text #12

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.2828. Min Act: -0.0000

Data Index: 1490455 (Python Code)

Max Activating Token Index: 655

Text #13

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.2461. Min Act: -0.0000

Data Index: 1391274 (Python Code)

Max Activating Token Index: 267

Text #14

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1451484 (Python Code)

Max Activating Token Index: 927

Text #15

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1487862 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1653961 (Python Code)

Max Activating Token Index: 255

Text #17

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.1246. Min Act: -0.0000

Data Index: 1412591 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.2609. Min Act: -0.0000

Data Index: 1398346 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 2.1120. Min Range: -2.1120

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1515337 (Python Code)

Max Activating Token Index: 144