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

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

Neuron 275 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3549. Min Range: -2.3549

Max Act: 2.3549. Min Act: -0.0000

Data Index: 1540327 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 2.3549. Min Range: -2.3549

Max Act: 2.1488. Min Act: -0.0000

Data Index: 1471520 (Python Code)

Max Activating Token Index: 980

Text #2

Max Range: 2.3549. Min Range: -2.3549

Max Act: 2.1564. Min Act: -0.0000

Data Index: 539259 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 2.3549. Min Range: -2.3549

Max Act: 2.0453. Min Act: -0.0000

Data Index: 1061853 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.9919. Min Act: -0.0000

Data Index: 675503 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.8806. Min Act: -0.0000

Data Index: 62726 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.8550. Min Act: -0.0000

Data Index: 987185 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.8702. Min Act: -0.0000

Data Index: 1517848 (Python Code)

Max Activating Token Index: 802

Text #8

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.9667. Min Act: -0.0000

Data Index: 375528 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.9200. Min Act: -0.0000

Data Index: 170624 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.9260. Min Act: -0.0000

Data Index: 1540874 (Python Code)

Max Activating Token Index: 188

Text #11

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.9000. Min Act: -0.0000

Data Index: 1463171 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.9731. Min Act: -0.0000

Data Index: 1211984 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.8748. Min Act: -0.0000

Data Index: 493069 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.7227. Min Act: -0.0000

Data Index: 1407734 (Python Code)

Max Activating Token Index: 611

Text #15

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.8032. Min Act: -0.0000

Data Index: 1500437 (Python Code)

Max Activating Token Index: 580

Text #16

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.8495. Min Act: -0.0001

Data Index: 1605520 (Python Code)

Max Activating Token Index: 430

Text #17

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.9462. Min Act: -0.0000

Data Index: 649744 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.7195. Min Act: -0.0000

Data Index: 154435 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 2.3549. Min Range: -2.3549

Max Act: 1.9934. Min Act: -0.0000

Data Index: 1362736 (Python Code)

Max Activating Token Index: 187