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

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

Neuron 3213 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.4534. Min Act: -0.0000

Data Index: 1629474 (Python Code)

Max Activating Token Index: 687

Text #1

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.5069. Min Act: -0.0000

Data Index: 1556331 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.5035. Min Act: -0.0000

Data Index: 1386320 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2355. Min Act: -0.0000

Data Index: 1367397 (Python Code)

Max Activating Token Index: 786

Text #4

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2584. Min Act: -0.0000

Data Index: 1616620 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1606735 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2655. Min Act: -0.0000

Data Index: 1515628 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1547470 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1392018 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1540031 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1404351 (Python Code)

Max Activating Token Index: 839

Text #11

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1619611 (Python Code)

Max Activating Token Index: 392

Text #12

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1627240 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1403454 (Python Code)

Max Activating Token Index: 207

Text #14

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1411728 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1421524 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1402812 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1570672 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1430960 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1638562 (Python Code)

Max Activating Token Index: 335