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

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

Neuron 4329 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.8155. Min Act: -0.0001

Data Index: 1557291 (Python Code)

Max Activating Token Index: 758

Text #1

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.6885. Min Act: -0.0001

Data Index: 1538972 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.6418. Min Act: -0.0001

Data Index: 1367402 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.5468. Min Act: -0.0001

Data Index: 1473995 (Python Code)

Max Activating Token Index: 491

Text #4

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.6985. Min Act: -0.0001

Data Index: 1449831 (Python Code)

Max Activating Token Index: 201

Text #5

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.5425. Min Act: -0.0001

Data Index: 1612207 (Python Code)

Max Activating Token Index: 915

Text #6

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.4877. Min Act: -0.0001

Data Index: 1632478 (Python Code)

Max Activating Token Index: 433

Text #7

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.5063. Min Act: -0.0001

Data Index: 1420331 (Python Code)

Max Activating Token Index: 593

Text #8

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.4245. Min Act: -0.0001

Data Index: 1452883 (Python Code)

Max Activating Token Index: 186

Text #9

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.4648. Min Act: -0.0001

Data Index: 1489677 (Python Code)

Max Activating Token Index: 314

Text #10

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.4441. Min Act: -0.0001

Data Index: 1480436 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.4681. Min Act: -0.0001

Data Index: 1518999 (Python Code)

Max Activating Token Index: 961

Text #12

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.4348. Min Act: -0.0001

Data Index: 1597703 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.2802. Min Act: -0.0001

Data Index: 1425724 (Python Code)

Max Activating Token Index: 876

Text #14

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.3489. Min Act: -0.0001

Data Index: 1472557 (Python Code)

Max Activating Token Index: 269

Text #15

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.3841. Min Act: -0.0001

Data Index: 1563610 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.4246. Min Act: -0.0001

Data Index: 1424790 (Python Code)

Max Activating Token Index: 515

Text #17

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.4027. Min Act: -0.0001

Data Index: 1422500 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.3129. Min Act: -0.0001

Data Index: 1382779 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.3582. Min Act: -0.0001

Data Index: 1375965 (Python Code)

Max Activating Token Index: 596