Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1007 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1385718 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2026. Min Act: -0.0001

Data Index: 1495585 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1617928 (Python Code)

Max Activating Token Index: 96

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2032. Min Act: -0.0001

Data Index: 1617836 (Python Code)

Max Activating Token Index: 860

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1419451 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1634347 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1611759 (Python Code)

Max Activating Token Index: 450

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1583447 (Python Code)

Max Activating Token Index: 218

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1903. Min Act: -0.0001

Data Index: 1476823 (Python Code)

Max Activating Token Index: 745

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1447606 (Python Code)

Max Activating Token Index: 62

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1470834 (Python Code)

Max Activating Token Index: 209

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1374352 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1480366 (Python Code)

Max Activating Token Index: 325

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1587201 (Python Code)

Max Activating Token Index: 513

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1435314 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1453148 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1732. Min Act: -0.0001

Data Index: 1499035 (Python Code)

Max Activating Token Index: 584

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1566942 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1548908 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1642782 (Python Code)

Max Activating Token Index: 871