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

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

Neuron 5250 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: 3.1111. Min Range: -3.1111

Max Act: 3.0911. Min Act: -0.0000

Data Index: 1564999 (Python Code)

Max Activating Token Index: 668

Text #1

Max Range: 3.1111. Min Range: -3.1111

Max Act: 3.1111. Min Act: -0.0000

Data Index: 1544283 (Python Code)

Max Activating Token Index: 691

Text #2

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.8748. Min Act: -0.0000

Data Index: 801439 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.6726. Min Act: -0.0000

Data Index: 1451799 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.6139. Min Act: -0.0000

Data Index: 1410142 (Python Code)

Max Activating Token Index: 393

Text #5

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.7634. Min Act: -0.0000

Data Index: 1415358 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.5946. Min Act: -0.0000

Data Index: 1601738 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.5605. Min Act: -0.0000

Data Index: 1496243 (Python Code)

Max Activating Token Index: 927

Text #8

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.5902. Min Act: -0.0000

Data Index: 1423502 (Python Code)

Max Activating Token Index: 455

Text #9

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.4413. Min Act: -0.0000

Data Index: 1369174 (Python Code)

Max Activating Token Index: 906

Text #10

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.7047. Min Act: -0.0000

Data Index: 1468622 (Python Code)

Max Activating Token Index: 472

Text #11

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.5731. Min Act: -0.0000

Data Index: 1557258 (Python Code)

Max Activating Token Index: 435

Text #12

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.5025. Min Act: -0.0000

Data Index: 1361573 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.5133. Min Act: -0.0000

Data Index: 1365467 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.2544. Min Act: -0.0000

Data Index: 135836 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.6468. Min Act: -0.0000

Data Index: 1462594 (Python Code)

Max Activating Token Index: 596

Text #16

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.7538. Min Act: -0.0000

Data Index: 1420933 (Python Code)

Max Activating Token Index: 535

Text #17

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.6159. Min Act: -0.0000

Data Index: 1571728 (Python Code)

Max Activating Token Index: 613

Text #18

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.7405. Min Act: -0.0000

Data Index: 1555424 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.5625. Min Act: -0.0000

Data Index: 1612678 (Python Code)

Max Activating Token Index: 103