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

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

Neuron 4821 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: 4.1210. Min Range: -4.1210

Max Act: 4.0639. Min Act: -0.0000

Data Index: 1394297 (Python Code)

Max Activating Token Index: 997

Text #1

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.9601. Min Act: -0.0000

Data Index: 1645314 (Python Code)

Max Activating Token Index: 787

Text #2

Max Range: 4.1210. Min Range: -4.1210

Max Act: 4.1210. Min Act: -0.0000

Data Index: 1501904 (Python Code)

Max Activating Token Index: 659

Text #3

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.9864. Min Act: -0.0000

Data Index: 1653629 (Python Code)

Max Activating Token Index: 980

Text #4

Max Range: 4.1210. Min Range: -4.1210

Max Act: 4.0811. Min Act: -0.0000

Data Index: 1384468 (Python Code)

Max Activating Token Index: 672

Text #5

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.6328. Min Act: -0.0000

Data Index: 1654713 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.7565. Min Act: -0.0000

Data Index: 1576235 (Python Code)

Max Activating Token Index: 793

Text #7

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.7036. Min Act: -0.0000

Data Index: 1436076 (Python Code)

Max Activating Token Index: 564

Text #8

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.4645. Min Act: -0.0000

Data Index: 1483677 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.6185. Min Act: -0.0000

Data Index: 1542565 (Python Code)

Max Activating Token Index: 393

Text #10

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.5844. Min Act: -0.0000

Data Index: 1542524 (Python Code)

Max Activating Token Index: 571

Text #11

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.4936. Min Act: -0.0000

Data Index: 1562992 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.4281. Min Act: -0.0000

Data Index: 1504695 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.1810. Min Act: -0.0000

Data Index: 1487575 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.2847. Min Act: -0.0000

Data Index: 1652210 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.2296. Min Act: -0.0000

Data Index: 1587202 (Python Code)

Max Activating Token Index: 590

Text #16

Max Range: 4.1210. Min Range: -4.1210

Max Act: 2.8815. Min Act: -0.0000

Data Index: 1497977 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 4.1210. Min Range: -4.1210

Max Act: 3.0542. Min Act: -0.0000

Data Index: 1644705 (Python Code)

Max Activating Token Index: 720

Text #18

Max Range: 4.1210. Min Range: -4.1210

Max Act: 2.9994. Min Act: -0.0000

Data Index: 1413776 (Python Code)

Max Activating Token Index: 200

Text #19

Max Range: 4.1210. Min Range: -4.1210

Max Act: 2.7427. Min Act: -0.0000

Data Index: 1398586 (Python Code)

Max Activating Token Index: 870