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

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

Neuron 2773 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.7816. Min Act: -0.0000

Data Index: 407107 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.7649. Min Act: -0.0000

Data Index: 115324 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6542. Min Act: -0.0000

Data Index: 204516 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6870. Min Act: -0.0000

Data Index: 840054 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6692. Min Act: -0.0000

Data Index: 157684 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1253413 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6459. Min Act: -0.0000

Data Index: 641850 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6151. Min Act: -0.0000

Data Index: 903211 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6404. Min Act: -0.0000

Data Index: 844271 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1286751 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1150483 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6184. Min Act: -0.0000

Data Index: 714739 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.5864. Min Act: -0.0000

Data Index: 200518 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.5358. Min Act: -0.0000

Data Index: 549456 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.5336. Min Act: -0.0000

Data Index: 406046 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1093009 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.5554. Min Act: -0.0000

Data Index: 335206 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.5347. Min Act: -0.0000

Data Index: 488153 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.5593. Min Act: -0.0000

Data Index: 752064 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.5578. Min Act: -0.0000

Data Index: 916151 (C4 (Web Text))

Max Activating Token Index: 700