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

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

Neuron 4397 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: 0.2556. Min Range: -0.2556

Max Act: 0.2556. Min Act: -0.0000

Data Index: 22519 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2034. Min Act: -0.0000

Data Index: 152202 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1497085 (Python Code)

Max Activating Token Index: 811

Text #3

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1956. Min Act: -0.0000

Data Index: 757645 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1863. Min Act: -0.0000

Data Index: 818462 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1799. Min Act: -0.0000

Data Index: 261483 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1878. Min Act: -0.0000

Data Index: 745229 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1606. Min Act: -0.0000

Data Index: 715677 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1012091 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1552. Min Act: -0.0000

Data Index: 672368 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1580. Min Act: -0.0000

Data Index: 504263 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1672. Min Act: -0.0000

Data Index: 222875 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1601. Min Act: -0.0000

Data Index: 888465 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1627. Min Act: -0.0000

Data Index: 324467 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1539. Min Act: -0.0000

Data Index: 561576 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1013208 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1556. Min Act: 0.0000

Data Index: 1225685 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1486. Min Act: -0.0000

Data Index: 503056 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1376550 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1493. Min Act: -0.0000

Data Index: 320864 (C4 (Web Text))

Max Activating Token Index: 445