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

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

Neuron 2752 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0573. Min Act: -0.0001

Data Index: 43562 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0511. Min Act: -0.0001

Data Index: 146155 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0470. Min Act: -0.0001

Data Index: 626992 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0001

Data Index: 846504 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1585450 (Python Code)

Max Activating Token Index: 465

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1100279 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0429. Min Act: -0.0001

Data Index: 749195 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0446. Min Act: -0.0001

Data Index: 725357 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0425. Min Act: -0.0001

Data Index: 555919 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0444. Min Act: -0.0001

Data Index: 529371 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1502745 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1553575 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1069032 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0372. Min Act: -0.0002

Data Index: 227091 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0405. Min Act: -0.0001

Data Index: 704436 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0433. Min Act: -0.0001

Data Index: 203730 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0394. Min Act: -0.0001

Data Index: 159037 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0343. Min Act: -0.0001

Data Index: 54302 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1199513 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0385. Min Act: -0.0001

Data Index: 700107 (C4 (Web Text))

Max Activating Token Index: 776