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

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

Neuron 5923 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.8947. Min Act: -0.0000

Data Index: 1603185 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.8694. Min Act: -0.0000

Data Index: 1503803 (Python Code)

Max Activating Token Index: 938

Text #2

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.7896. Min Act: -0.0000

Data Index: 1548473 (Python Code)

Max Activating Token Index: 503

Text #3

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.8416. Min Act: -0.0000

Data Index: 1431689 (Python Code)

Max Activating Token Index: 448

Text #4

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.5769. Min Act: -0.0000

Data Index: 1400473 (Python Code)

Max Activating Token Index: 752

Text #5

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1620788 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1391509 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.4930. Min Act: -0.0000

Data Index: 1578360 (Python Code)

Max Activating Token Index: 216

Text #8

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.4915. Min Act: -0.0000

Data Index: 1448947 (Python Code)

Max Activating Token Index: 65

Text #9

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.5395. Min Act: -0.0000

Data Index: 1434004 (Python Code)

Max Activating Token Index: 259

Text #10

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1385217 (Python Code)

Max Activating Token Index: 660

Text #11

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.2498. Min Act: -0.0000

Data Index: 132820 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1501554 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1414063 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1497571 (Python Code)

Max Activating Token Index: 974

Text #15

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1559. Min Act: -0.0000

Data Index: 1572071 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1520886 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1385870 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1532757 (Python Code)

Max Activating Token Index: 329

Text #19

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1416658 (Python Code)

Max Activating Token Index: 952