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

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

Neuron 3429 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1413. Min Act: -0.0002

Data Index: 1031717 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1618. Min Act: -0.0002

Data Index: 978407 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1451. Min Act: -0.0002

Data Index: 303062 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1449. Min Act: -0.0002

Data Index: 1108942 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1577. Min Act: -0.0002

Data Index: 621702 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1490426 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1427. Min Act: -0.0002

Data Index: 407188 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1475. Min Act: -0.0002

Data Index: 603055 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1475. Min Act: -0.0002

Data Index: 582497 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1525. Min Act: -0.0002

Data Index: 1645930 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1510. Min Act: -0.0002

Data Index: 1450195 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1371. Min Act: -0.0002

Data Index: 954922 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1467. Min Act: -0.0002

Data Index: 1346177 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1511. Min Act: -0.0002

Data Index: 17484 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1462. Min Act: -0.0002

Data Index: 242776 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1569. Min Act: -0.0002

Data Index: 146616 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1497. Min Act: -0.0002

Data Index: 563028 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1554. Min Act: -0.0002

Data Index: 1052052 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1093595 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1433. Min Act: -0.0002

Data Index: 735269 (C4 (Web Text))

Max Activating Token Index: 25