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

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

Neuron 2342 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: 1.3912. Min Range: -1.3912

Max Act: 1.3552. Min Act: -0.0001

Data Index: 1389201 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.3912. Min Act: -0.0001

Data Index: 1585883 (Python Code)

Max Activating Token Index: 221

Text #2

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2345. Min Act: -0.0001

Data Index: 1565367 (Python Code)

Max Activating Token Index: 310

Text #3

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0891. Min Act: -0.0001

Data Index: 1370760 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0708. Min Act: -0.0001

Data Index: 1568886 (Python Code)

Max Activating Token Index: 264

Text #5

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0276. Min Act: -0.0001

Data Index: 1585760 (Python Code)

Max Activating Token Index: 116

Text #6

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1634. Min Act: -0.0000

Data Index: 1552928 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.3040. Min Act: -0.0001

Data Index: 1560644 (Python Code)

Max Activating Token Index: 203

Text #8

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.3368. Min Act: -0.0001

Data Index: 1629153 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0130. Min Act: -0.0001

Data Index: 1623575 (Python Code)

Max Activating Token Index: 700

Text #10

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1437. Min Act: -0.0001

Data Index: 1510443 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0670. Min Act: -0.0001

Data Index: 1495174 (Python Code)

Max Activating Token Index: 430

Text #12

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0647. Min Act: -0.0001

Data Index: 1511294 (Python Code)

Max Activating Token Index: 561

Text #13

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1538. Min Act: -0.0001

Data Index: 1570443 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1585. Min Act: -0.0001

Data Index: 1601723 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1627. Min Act: -0.0001

Data Index: 1546246 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1518. Min Act: -0.0000

Data Index: 1599008 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1489. Min Act: -0.0001

Data Index: 1439595 (Python Code)

Max Activating Token Index: 203

Text #18

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1058. Min Act: -0.0001

Data Index: 1504639 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1624983 (Python Code)

Max Activating Token Index: 528