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

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

Neuron 4434 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.7017. Min Act: -0.0001

Data Index: 1389985 (Python Code)

Max Activating Token Index: 366

Text #1

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.6430. Min Act: -0.0001

Data Index: 1642669 (Python Code)

Max Activating Token Index: 390

Text #2

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.6787. Min Act: -0.0001

Data Index: 1527577 (Python Code)

Max Activating Token Index: 940

Text #3

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.6541. Min Act: -0.0001

Data Index: 1625044 (Python Code)

Max Activating Token Index: 177

Text #4

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.6337. Min Act: -0.0001

Data Index: 1410031 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5984. Min Act: -0.0001

Data Index: 1392937 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.6184. Min Act: -0.0001

Data Index: 1546685 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.6698. Min Act: -0.0001

Data Index: 1552498 (Python Code)

Max Activating Token Index: 676

Text #8

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5702. Min Act: -0.0001

Data Index: 1459225 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1384656 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1506168 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1641010 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5788. Min Act: -0.0001

Data Index: 1433551 (Python Code)

Max Activating Token Index: 454

Text #13

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5606. Min Act: -0.0001

Data Index: 1449565 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5489. Min Act: -0.0001

Data Index: 1633841 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5448. Min Act: -0.0001

Data Index: 1425238 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5801. Min Act: -0.0001

Data Index: 1395092 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5781. Min Act: -0.0001

Data Index: 1608053 (Python Code)

Max Activating Token Index: 248

Text #18

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.5331. Min Act: -0.0001

Data Index: 1500909 (Python Code)

Max Activating Token Index: 492

Text #19

Max Range: 0.7017. Min Range: -0.7017

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1397406 (Python Code)

Max Activating Token Index: 267