Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1295 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0875. Min Act: -0.0004

Data Index: 1596693 (Python Code)

Max Activating Token Index: 442

Text #1

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1397568 (Python Code)

Max Activating Token Index: 678

Text #2

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0598. Min Act: -0.0002

Data Index: 385510 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1627534 (Python Code)

Max Activating Token Index: 946

Text #4

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1435000 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1472429 (Python Code)

Max Activating Token Index: 923

Text #6

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1587381 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1266816 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0511. Min Act: -0.0002

Data Index: 185270 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1460663 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1586082 (Python Code)

Max Activating Token Index: 591

Text #11

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1607197 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0537. Min Act: -0.0002

Data Index: 809956 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1402854 (Python Code)

Max Activating Token Index: 167

Text #14

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0505. Min Act: -0.0003

Data Index: 988414 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1190148 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1655024 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1484445 (Python Code)

Max Activating Token Index: 988

Text #18

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1382322 (Python Code)

Max Activating Token Index: 390

Text #19

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1644761 (Python Code)

Max Activating Token Index: 25