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

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

Neuron 2129 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4515. Min Range: -3.4515

Max Act: 3.4515. Min Act: -0.0000

Data Index: 1644966 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 3.4515. Min Range: -3.4515

Max Act: 3.2093. Min Act: -0.0000

Data Index: 1446922 (Python Code)

Max Activating Token Index: 945

Text #2

Max Range: 3.4515. Min Range: -3.4515

Max Act: 3.0340. Min Act: -0.0000

Data Index: 1472931 (Python Code)

Max Activating Token Index: 852

Text #3

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.7717. Min Act: -0.0001

Data Index: 1645945 (Python Code)

Max Activating Token Index: 245

Text #4

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.9068. Min Act: -0.0000

Data Index: 1638689 (Python Code)

Max Activating Token Index: 533

Text #5

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.4701. Min Act: -0.0001

Data Index: 1381456 (Python Code)

Max Activating Token Index: 465

Text #6

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.5659. Min Act: -0.0001

Data Index: 1398135 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.3000. Min Act: -0.0001

Data Index: 1384302 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.3688. Min Act: -0.0000

Data Index: 1528740 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.2026. Min Act: -0.0001

Data Index: 1578982 (Python Code)

Max Activating Token Index: 675

Text #10

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.3486. Min Act: -0.0000

Data Index: 1466927 (Python Code)

Max Activating Token Index: 725

Text #11

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.2604. Min Act: -0.0001

Data Index: 1560646 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.0679. Min Act: -0.0000

Data Index: 1408721 (Python Code)

Max Activating Token Index: 230

Text #13

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.2173. Min Act: -0.0000

Data Index: 1519552 (Python Code)

Max Activating Token Index: 245

Text #14

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.1158. Min Act: -0.0001

Data Index: 1648569 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.2177. Min Act: -0.0001

Data Index: 1487721 (Python Code)

Max Activating Token Index: 811

Text #16

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.1916. Min Act: -0.0001

Data Index: 1631244 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 3.4515. Min Range: -3.4515

Max Act: 1.9464. Min Act: -0.0000

Data Index: 1614435 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.1554. Min Act: -0.0000

Data Index: 1610815 (Python Code)

Max Activating Token Index: 399

Text #19

Max Range: 3.4515. Min Range: -3.4515

Max Act: 2.1611. Min Act: -0.0000

Data Index: 1413719 (Python Code)

Max Activating Token Index: 56