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

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

Neuron 3462 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: 1.8228. Min Range: -1.8228

Max Act: 1.8228. Min Act: -0.0001

Data Index: 1452759 (Python Code)

Max Activating Token Index: 986

Text #1

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.3583. Min Act: -0.0001

Data Index: 1407024 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.6255. Min Act: -0.0001

Data Index: 1595768 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.4574. Min Act: -0.0001

Data Index: 1646560 (Python Code)

Max Activating Token Index: 724

Text #4

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.6445. Min Act: -0.0001

Data Index: 1454830 (Python Code)

Max Activating Token Index: 765

Text #5

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.5044. Min Act: -0.0001

Data Index: 1579357 (Python Code)

Max Activating Token Index: 384

Text #6

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.4878. Min Act: -0.0001

Data Index: 1188010 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.3898. Min Act: -0.0001

Data Index: 1642847 (Python Code)

Max Activating Token Index: 764

Text #8

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.4090. Min Act: -0.0001

Data Index: 1396024 (Python Code)

Max Activating Token Index: 427

Text #9

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.3889. Min Act: -0.0001

Data Index: 1439081 (Python Code)

Max Activating Token Index: 771

Text #10

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.3645. Min Act: -0.0001

Data Index: 1603505 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.4680. Min Act: -0.0001

Data Index: 1527475 (Python Code)

Max Activating Token Index: 962

Text #12

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.3301. Min Act: -0.0001

Data Index: 132620 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.3156. Min Act: -0.0001

Data Index: 1492777 (Python Code)

Max Activating Token Index: 613

Text #14

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.4556. Min Act: -0.0001

Data Index: 1337409 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.4977. Min Act: -0.0001

Data Index: 1377234 (Python Code)

Max Activating Token Index: 739

Text #16

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.3129. Min Act: -0.0001

Data Index: 1036506 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.4523. Min Act: -0.0001

Data Index: 1480028 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.3711. Min Act: -0.0001

Data Index: 1485391 (Python Code)

Max Activating Token Index: 918

Text #19

Max Range: 1.8228. Min Range: -1.8228

Max Act: 1.2913. Min Act: -0.0001

Data Index: 1556684 (Python Code)

Max Activating Token Index: 337