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

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

Neuron 4858 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2861. Min Range: -2.2861

Max Act: 2.1592. Min Act: -0.0000

Data Index: 1420060 (Python Code)

Max Activating Token Index: 813

Text #1

Max Range: 2.2861. Min Range: -2.2861

Max Act: 2.2861. Min Act: -0.0000

Data Index: 1364685 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 2.2861. Min Range: -2.2861

Max Act: 2.2593. Min Act: -0.0000

Data Index: 1390468 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 2.2861. Min Range: -2.2861

Max Act: 2.0306. Min Act: -0.0000

Data Index: 1362031 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.9429. Min Act: -0.0000

Data Index: 1405005 (Python Code)

Max Activating Token Index: 678

Text #5

Max Range: 2.2861. Min Range: -2.2861

Max Act: 2.1227. Min Act: -0.0000

Data Index: 1403508 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.9719. Min Act: -0.0000

Data Index: 1384277 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.9472. Min Act: -0.0000

Data Index: 1492789 (Python Code)

Max Activating Token Index: 573

Text #8

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7585. Min Act: -0.0000

Data Index: 1588348 (Python Code)

Max Activating Token Index: 741

Text #9

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.8400. Min Act: -0.0000

Data Index: 1555142 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.8386. Min Act: -0.0000

Data Index: 1454530 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7683. Min Act: -0.0000

Data Index: 1553028 (Python Code)

Max Activating Token Index: 373

Text #12

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7587. Min Act: -0.0000

Data Index: 1491629 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7503. Min Act: -0.0000

Data Index: 1468814 (Python Code)

Max Activating Token Index: 132

Text #14

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7555. Min Act: -0.0000

Data Index: 682880 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7632. Min Act: -0.0000

Data Index: 1397112 (Python Code)

Max Activating Token Index: 795

Text #16

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7398. Min Act: -0.0000

Data Index: 1365264 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7342. Min Act: -0.0000

Data Index: 1534511 (Python Code)

Max Activating Token Index: 944

Text #18

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7006. Min Act: -0.0000

Data Index: 1992 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.7906. Min Act: -0.0000

Data Index: 1421528 (Python Code)

Max Activating Token Index: 294