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

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

Neuron 1244 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: 0.7998. Min Range: -0.7998

Max Act: 0.7842. Min Act: -0.0000

Data Index: 793483 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7998. Min Act: -0.0000

Data Index: 253808 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1098268 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7323. Min Act: -0.0000

Data Index: 819425 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6642. Min Act: -0.0000

Data Index: 529670 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6394. Min Act: -0.0000

Data Index: 862634 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1032789 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1346245 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1157132 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6334. Min Act: -0.0000

Data Index: 585701 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5959. Min Act: -0.0000

Data Index: 452302 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1224745 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5558. Min Act: -0.0000

Data Index: 37754 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5287. Min Act: -0.0000

Data Index: 527165 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1576632 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5571. Min Act: -0.0000

Data Index: 686386 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5318. Min Act: -0.0000

Data Index: 423190 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5288. Min Act: -0.0000

Data Index: 483421 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5439. Min Act: -0.0000

Data Index: 571841 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5459. Min Act: -0.0000

Data Index: 342441 (C4 (Web Text))

Max Activating Token Index: 137