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

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

Neuron 4919 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: 4.1441. Min Range: -4.1441

Max Act: 4.1441. Min Act: -0.0000

Data Index: 1439745 (Python Code)

Max Activating Token Index: 771

Text #1

Max Range: 4.1441. Min Range: -4.1441

Max Act: 4.0736. Min Act: -0.0000

Data Index: 1380498 (Python Code)

Max Activating Token Index: 590

Text #2

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.9714. Min Act: -0.0000

Data Index: 1591391 (Python Code)

Max Activating Token Index: 759

Text #3

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.7432. Min Act: -0.0000

Data Index: 1482227 (Python Code)

Max Activating Token Index: 996

Text #4

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.6323. Min Act: -0.0000

Data Index: 1510947 (Python Code)

Max Activating Token Index: 820

Text #5

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.2701. Min Act: -0.0000

Data Index: 1573883 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.7209. Min Act: -0.0000

Data Index: 1576138 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.6858. Min Act: -0.0000

Data Index: 1467140 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.4418. Min Act: -0.0000

Data Index: 1538292 (Python Code)

Max Activating Token Index: 684

Text #9

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.5947. Min Act: -0.0000

Data Index: 1435960 (Python Code)

Max Activating Token Index: 726

Text #10

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.5768. Min Act: -0.0000

Data Index: 1409392 (Python Code)

Max Activating Token Index: 1011

Text #11

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.2212. Min Act: -0.0000

Data Index: 1593118 (Python Code)

Max Activating Token Index: 669

Text #12

Max Range: 4.1441. Min Range: -4.1441

Max Act: 2.9519. Min Act: -0.0000

Data Index: 1445575 (Python Code)

Max Activating Token Index: 1011

Text #13

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.0812. Min Act: -0.0000

Data Index: 1442368 (Python Code)

Max Activating Token Index: 507

Text #14

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.0804. Min Act: -0.0000

Data Index: 1616406 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.2137. Min Act: -0.0000

Data Index: 1636713 (Python Code)

Max Activating Token Index: 549

Text #16

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.1961. Min Act: -0.0000

Data Index: 1394197 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.1990. Min Act: -0.0000

Data Index: 1538874 (Python Code)

Max Activating Token Index: 170

Text #18

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.2893. Min Act: -0.0000

Data Index: 1494335 (Python Code)

Max Activating Token Index: 910

Text #19

Max Range: 4.1441. Min Range: -4.1441

Max Act: 3.0284. Min Act: -0.0000

Data Index: 505072 (C4 (Web Text))

Max Activating Token Index: 431