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

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

Neuron 3192 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: 5.8000. Min Range: -5.8000

Max Act: 5.6499. Min Act: -0.0000

Data Index: 1425594 (Python Code)

Max Activating Token Index: 978

Text #1

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.6041. Min Act: -0.0000

Data Index: 1383733 (Python Code)

Max Activating Token Index: 194

Text #2

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.8000. Min Act: -0.0000

Data Index: 1395829 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.3601. Min Act: -0.0000

Data Index: 1501027 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.8804. Min Act: -0.0000

Data Index: 1647128 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.3328. Min Act: -0.0000

Data Index: 1655592 (Python Code)

Max Activating Token Index: 318

Text #6

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.2586. Min Act: -0.0000

Data Index: 1369530 (Python Code)

Max Activating Token Index: 99

Text #7

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.2183. Min Act: -0.0000

Data Index: 1597415 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.0446. Min Act: -0.0000

Data Index: 1489759 (Python Code)

Max Activating Token Index: 545

Text #9

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.7881. Min Act: -0.0000

Data Index: 1619762 (Python Code)

Max Activating Token Index: 653

Text #10

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.0756. Min Act: -0.0000

Data Index: 1643203 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.4921. Min Act: -0.0000

Data Index: 1579803 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.1527. Min Act: -0.0000

Data Index: 1593553 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.4727. Min Act: -0.0000

Data Index: 1514349 (Python Code)

Max Activating Token Index: 621

Text #14

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.4532. Min Act: -0.0000

Data Index: 1517587 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.5845. Min Act: -0.0000

Data Index: 1516748 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.6136. Min Act: -0.0000

Data Index: 1605349 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.3667. Min Act: -0.0000

Data Index: 1407953 (Python Code)

Max Activating Token Index: 882

Text #18

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.4587. Min Act: -0.0000

Data Index: 1502466 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.2861. Min Act: -0.0000

Data Index: 1557213 (Python Code)

Max Activating Token Index: 25