Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2651 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0000

Data Index: 611546 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0654. Min Act: -0.0000

Data Index: 906362 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0595. Min Act: -0.0001

Data Index: 900962 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1537069 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1233593 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0578. Min Act: -0.0001

Data Index: 115534 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0534. Min Act: -0.0001

Data Index: 953801 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0547. Min Act: -0.0000

Data Index: 1363470 (Python Code)

Max Activating Token Index: 677

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0540. Min Act: -0.0001

Data Index: 228330 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0517. Min Act: -0.0000

Data Index: 713339 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1344311 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0501. Min Act: -0.0000

Data Index: 825229 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1198184 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0516. Min Act: -0.0000

Data Index: 1319588 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0462. Min Act: -0.0001

Data Index: 829765 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0501. Min Act: -0.0000

Data Index: 899329 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0473. Min Act: -0.0000

Data Index: 80634 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0475. Min Act: -0.0000

Data Index: 333881 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0503. Min Act: -0.0000

Data Index: 881547 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1589237 (Python Code)

Max Activating Token Index: 428