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

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

Neuron 919 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1462. Min Range: -5.1462

Max Act: 5.1083. Min Act: -0.0000

Data Index: 1613933 (Python Code)

Max Activating Token Index: 696

Text #1

Max Range: 5.1462. Min Range: -5.1462

Max Act: 5.1462. Min Act: -0.0000

Data Index: 1361362 (Python Code)

Max Activating Token Index: 539

Text #2

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.9387. Min Act: -0.0000

Data Index: 1508536 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.8717. Min Act: -0.0000

Data Index: 1487203 (Python Code)

Max Activating Token Index: 861

Text #4

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.9887. Min Act: -0.0000

Data Index: 928886 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.6012. Min Act: -0.0000

Data Index: 1525356 (Python Code)

Max Activating Token Index: 200

Text #6

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.5807. Min Act: -0.0000

Data Index: 1506430 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.6328. Min Act: -0.0000

Data Index: 1621287 (Python Code)

Max Activating Token Index: 257

Text #8

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.6647. Min Act: -0.0000

Data Index: 1417069 (Python Code)

Max Activating Token Index: 620

Text #9

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.6231. Min Act: -0.0000

Data Index: 1619513 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.5775. Min Act: -0.0000

Data Index: 1457750 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.4879. Min Act: -0.0000

Data Index: 1558580 (Python Code)

Max Activating Token Index: 351

Text #12

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.2467. Min Act: -0.0000

Data Index: 1563655 (Python Code)

Max Activating Token Index: 621

Text #13

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.4549. Min Act: -0.0000

Data Index: 1544630 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.5994. Min Act: -0.0000

Data Index: 1514898 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.4022. Min Act: -0.0000

Data Index: 1363890 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.1696. Min Act: -0.0000

Data Index: 1637514 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.3508. Min Act: -0.0000

Data Index: 1583368 (Python Code)

Max Activating Token Index: 266

Text #18

Max Range: 5.1462. Min Range: -5.1462

Max Act: 4.2981. Min Act: -0.0000

Data Index: 1647725 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 5.1462. Min Range: -5.1462

Max Act: 3.8754. Min Act: -0.0000

Data Index: 1409588 (Python Code)

Max Activating Token Index: 340