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

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

Neuron 1870 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0000

Data Index: 512766 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0518. Min Act: -0.0000

Data Index: 965016 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0489. Min Act: -0.0000

Data Index: 446865 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1524979 (Python Code)

Max Activating Token Index: 113

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0525. Min Act: -0.0000

Data Index: 250865 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0478. Min Act: -0.0000

Data Index: 842271 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1279081 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0465. Min Act: -0.0000

Data Index: 168262 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0495. Min Act: -0.0000

Data Index: 645731 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0464. Min Act: -0.0000

Data Index: 172810 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0502. Min Act: -0.0000

Data Index: 905706 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1355003 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1085455 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0444. Min Act: -0.0000

Data Index: 243310 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0437. Min Act: -0.0000

Data Index: 1612670 (Python Code)

Max Activating Token Index: 392

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1253348 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0486. Min Act: -0.0000

Data Index: 910417 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0460. Min Act: -0.0000

Data Index: 790810 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0430. Min Act: -0.0000

Data Index: 1347249 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0439. Min Act: -0.0000

Data Index: 370482 (C4 (Web Text))

Max Activating Token Index: 699