Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2033 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1570758 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0551. Min Act: -0.0000

Data Index: 495314 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0526. Min Act: 0.0003

Data Index: 1510486 (Python Code)

Max Activating Token Index: 589

Text #3

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1628044 (Python Code)

Max Activating Token Index: 571

Text #4

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1363458 (Python Code)

Max Activating Token Index: 378

Text #5

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1048362 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0489. Min Act: -0.0000

Data Index: 361141 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1604718 (Python Code)

Max Activating Token Index: 954

Text #8

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0507. Min Act: 0.0003

Data Index: 1390247 (Python Code)

Max Activating Token Index: 871

Text #9

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0455. Min Act: -0.0000

Data Index: 1577571 (Python Code)

Max Activating Token Index: 532

Text #10

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0465. Min Act: 0.0003

Data Index: 1522060 (Python Code)

Max Activating Token Index: 421

Text #11

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1548022 (Python Code)

Max Activating Token Index: 383

Text #12

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0446. Min Act: -0.0000

Data Index: 1436201 (Python Code)

Max Activating Token Index: 883

Text #13

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1380939 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0469. Min Act: 0.0003

Data Index: 1651328 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1608603 (Python Code)

Max Activating Token Index: 905

Text #16

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1449449 (Python Code)

Max Activating Token Index: 1002

Text #17

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1431935 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0435. Min Act: -0.0000

Data Index: 1489263 (Python Code)

Max Activating Token Index: 607

Text #19

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0436. Min Act: 0.0000

Data Index: 1104857 (C4 (Web Text))

Max Activating Token Index: 902