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

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

Neuron 4747 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2618. Min Act: -0.0000

Data Index: 325221 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1331529 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2324. Min Act: -0.0000

Data Index: 947613 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1928. Min Act: -0.0000

Data Index: 185648 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2052. Min Act: -0.0000

Data Index: 690165 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1680. Min Act: -0.0000

Data Index: 611234 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1626390 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1710. Min Act: -0.0000

Data Index: 931059 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1424. Min Act: -0.0000

Data Index: 940841 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1637. Min Act: -0.0000

Data Index: 103414 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1663. Min Act: -0.0000

Data Index: 110800 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1774. Min Act: -0.0000

Data Index: 84748 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1690. Min Act: -0.0000

Data Index: 924975 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1481. Min Act: -0.0000

Data Index: 169882 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1073686 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1415674 (Python Code)

Max Activating Token Index: 715

Text #16

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1523. Min Act: -0.0000

Data Index: 2216 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1492. Min Act: -0.0000

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1123207 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1471. Min Act: -0.0000

Data Index: 627214 (C4 (Web Text))

Max Activating Token Index: 713