Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1763 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6917. Min Range: -2.6917

Max Act: 2.6917. Min Act: -0.0000

Data Index: 1375834 (Python Code)

Max Activating Token Index: 948

Text #1

Max Range: 2.6917. Min Range: -2.6917

Max Act: 2.0246. Min Act: -0.0000

Data Index: 1640870 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.8467. Min Act: -0.0000

Data Index: 1531937 (Python Code)

Max Activating Token Index: 869

Text #3

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.6507. Min Act: -0.0000

Data Index: 1542912 (Python Code)

Max Activating Token Index: 717

Text #4

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1505093 (Python Code)

Max Activating Token Index: 686

Text #5

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1526805 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.7043. Min Act: -0.0000

Data Index: 1577115 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.8526. Min Act: -0.0000

Data Index: 1562331 (Python Code)

Max Activating Token Index: 432

Text #8

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.7798. Min Act: -0.0000

Data Index: 1410193 (Python Code)

Max Activating Token Index: 361

Text #9

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.7888. Min Act: -0.0000

Data Index: 1410748 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.6149. Min Act: -0.0000

Data Index: 1625569 (Python Code)

Max Activating Token Index: 152

Text #11

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.7764. Min Act: -0.0000

Data Index: 1495178 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.7811. Min Act: -0.0000

Data Index: 1511148 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.7443. Min Act: -0.0000

Data Index: 1615242 (Python Code)

Max Activating Token Index: 809

Text #14

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.7582. Min Act: -0.0000

Data Index: 1588001 (Python Code)

Max Activating Token Index: 729

Text #15

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.4937. Min Act: -0.0000

Data Index: 1650342 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.6331. Min Act: -0.0000

Data Index: 1420281 (Python Code)

Max Activating Token Index: 435

Text #17

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.5965. Min Act: -0.0000

Data Index: 1516588 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.6663. Min Act: -0.0000

Data Index: 1366032 (Python Code)

Max Activating Token Index: 615

Text #19

Max Range: 2.6917. Min Range: -2.6917

Max Act: 1.9828. Min Act: -0.0000

Data Index: 1491444 (Python Code)

Max Activating Token Index: 222