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

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

Neuron 4905 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.1904. Min Act: -0.0000

Data Index: 1364253 (Python Code)

Max Activating Token Index: 324

Text #1

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.0666. Min Act: -0.0000

Data Index: 1428637 (Python Code)

Max Activating Token Index: 806

Text #2

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.1540. Min Act: -0.0000

Data Index: 1627945 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.1569. Min Act: -0.0000

Data Index: 1636877 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.0038. Min Act: -0.0000

Data Index: 1581896 (Python Code)

Max Activating Token Index: 606

Text #5

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.1238. Min Act: -0.0000

Data Index: 1633827 (Python Code)

Max Activating Token Index: 552

Text #6

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.0646. Min Act: -0.0000

Data Index: 833952 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1595529 (Python Code)

Max Activating Token Index: 253

Text #8

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.9246. Min Act: -0.0000

Data Index: 1585297 (Python Code)

Max Activating Token Index: 878

Text #9

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.0790. Min Act: -0.0000

Data Index: 1485436 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.0159. Min Act: -0.0000

Data Index: 1483354 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 2.1904. Min Range: -2.1904

Max Act: 2.0798. Min Act: -0.0000

Data Index: 1646448 (Python Code)

Max Activating Token Index: 723

Text #12

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.8575. Min Act: -0.0000

Data Index: 1486993 (Python Code)

Max Activating Token Index: 290

Text #13

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1601626 (Python Code)

Max Activating Token Index: 722

Text #14

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1402246 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.8449. Min Act: -0.0000

Data Index: 1410182 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1561926 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.8779. Min Act: -0.0000

Data Index: 339353 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1389806 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 2.1904. Min Range: -2.1904

Max Act: 1.7492. Min Act: -0.0000

Data Index: 1455897 (Python Code)

Max Activating Token Index: 297