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

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

Neuron 5170 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: 5.1106. Min Range: -5.1106

Max Act: 4.9311. Min Act: -0.0000

Data Index: 1465966 (Python Code)

Max Activating Token Index: 817

Text #1

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.7595. Min Act: -0.0000

Data Index: 1492787 (Python Code)

Max Activating Token Index: 879

Text #2

Max Range: 5.1106. Min Range: -5.1106

Max Act: 5.1106. Min Act: -0.0000

Data Index: 1383408 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.6737. Min Act: -0.0000

Data Index: 1398390 (Python Code)

Max Activating Token Index: 453

Text #4

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.4638. Min Act: -0.0000

Data Index: 1420962 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.4930. Min Act: -0.0000

Data Index: 1501371 (Python Code)

Max Activating Token Index: 743

Text #6

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.2988. Min Act: -0.0000

Data Index: 1474014 (Python Code)

Max Activating Token Index: 708

Text #7

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.2764. Min Act: -0.0000

Data Index: 1411446 (Python Code)

Max Activating Token Index: 361

Text #8

Max Range: 5.1106. Min Range: -5.1106

Max Act: 3.7953. Min Act: -0.0000

Data Index: 1606160 (Python Code)

Max Activating Token Index: 270

Text #9

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.4127. Min Act: -0.0000

Data Index: 1447410 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.8949. Min Act: -0.0000

Data Index: 1405688 (Python Code)

Max Activating Token Index: 864

Text #11

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.3587. Min Act: -0.0000

Data Index: 1503532 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 5.1106. Min Range: -5.1106

Max Act: 3.8845. Min Act: -0.0000

Data Index: 1365705 (Python Code)

Max Activating Token Index: 826

Text #13

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.4648. Min Act: -0.0000

Data Index: 1390491 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.1005. Min Act: -0.0000

Data Index: 1605521 (Python Code)

Max Activating Token Index: 576

Text #15

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.0963. Min Act: -0.0000

Data Index: 1457595 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.2329. Min Act: -0.0000

Data Index: 1397371 (Python Code)

Max Activating Token Index: 847

Text #17

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.2032. Min Act: -0.0000

Data Index: 1579041 (Python Code)

Max Activating Token Index: 560

Text #18

Max Range: 5.1106. Min Range: -5.1106

Max Act: 3.8515. Min Act: -0.0000

Data Index: 1544357 (Python Code)

Max Activating Token Index: 198

Text #19

Max Range: 5.1106. Min Range: -5.1106

Max Act: 4.1925. Min Act: -0.0000

Data Index: 1425460 (Python Code)

Max Activating Token Index: 910