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

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

Neuron 4586 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4616. Min Act: -0.0000

Data Index: 47064 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3774. Min Act: -0.0000

Data Index: 197839 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1225478 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1062849 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2977. Min Act: -0.0000

Data Index: 581746 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1210163 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2381. Min Act: -0.0000

Data Index: 192793 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2848. Min Act: -0.0000

Data Index: 950800 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2761. Min Act: -0.0000

Data Index: 668272 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2829. Min Act: -0.0000

Data Index: 122513 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2601. Min Act: -0.0000

Data Index: 43529 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1179469 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2558. Min Act: -0.0000

Data Index: 78554 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2239. Min Act: -0.0000

Data Index: 709375 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2261. Min Act: -0.0000

Data Index: 77648 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2329. Min Act: -0.0000

Data Index: 640821 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2293. Min Act: -0.0000

Data Index: 815459 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2258. Min Act: -0.0000

Data Index: 106359 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1187442 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.2141. Min Act: -0.0000

Data Index: 66170 (C4 (Web Text))

Max Activating Token Index: 802