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

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

Neuron 1667 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: 2.7853. Min Range: -2.7853

Max Act: 2.7853. Min Act: -0.0000

Data Index: 1551526 (Python Code)

Max Activating Token Index: 97

Text #1

Max Range: 2.7853. Min Range: -2.7853

Max Act: 2.6076. Min Act: -0.0000

Data Index: 1532286 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 2.7853. Min Range: -2.7853

Max Act: 2.1817. Min Act: -0.0000

Data Index: 1553797 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.7374. Min Act: -0.0000

Data Index: 1559915 (Python Code)

Max Activating Token Index: 773

Text #4

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.6607. Min Act: -0.0000

Data Index: 1546992 (Python Code)

Max Activating Token Index: 754

Text #5

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1396202 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1518487 (Python Code)

Max Activating Token Index: 932

Text #7

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.5520. Min Act: -0.0000

Data Index: 1447546 (Python Code)

Max Activating Token Index: 484

Text #8

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.5343. Min Act: -0.0000

Data Index: 1639302 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.5042. Min Act: -0.0000

Data Index: 1549736 (Python Code)

Max Activating Token Index: 959

Text #10

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.3906. Min Act: -0.0000

Data Index: 1601055 (Python Code)

Max Activating Token Index: 259

Text #11

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.4413. Min Act: -0.0000

Data Index: 1419945 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.3098. Min Act: -0.0000

Data Index: 1512633 (Python Code)

Max Activating Token Index: 265

Text #13

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1605763 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1552023 (Python Code)

Max Activating Token Index: 1009

Text #15

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.2203. Min Act: -0.0000

Data Index: 1527548 (Python Code)

Max Activating Token Index: 751

Text #16

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1364809 (Python Code)

Max Activating Token Index: 621

Text #17

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1367512 (Python Code)

Max Activating Token Index: 895

Text #18

Max Range: 2.7853. Min Range: -2.7853

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1412922 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 2.7853. Min Range: -2.7853

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1604967 (Python Code)

Max Activating Token Index: 18