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

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

Neuron 5125 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6973. Min Act: -0.0000

Data Index: 333431 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.4863. Min Act: -0.0000

Data Index: 359711 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.3387. Min Act: -0.0000

Data Index: 635099 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.2953. Min Act: -0.0000

Data Index: 785225 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.2387. Min Act: -0.0000

Data Index: 1261640 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.1495. Min Act: -0.0000

Data Index: 956367 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.1317. Min Act: -0.0000

Data Index: 888897 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.1159. Min Act: -0.0000

Data Index: 1263859 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.1106. Min Act: -0.0000

Data Index: 433936 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.0855. Min Act: -0.0000

Data Index: 447543 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.1362. Min Act: -0.0000

Data Index: 852617 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.0468. Min Act: -0.0000

Data Index: 490222 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.0502. Min Act: -0.0000

Data Index: 416292 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.0416. Min Act: -0.0000

Data Index: 581602 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1059001 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1174087 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.6973. Min Range: -1.6973

Max Act: 0.9643. Min Act: -0.0000

Data Index: 151689 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 1.6973. Min Range: -1.6973

Max Act: 0.9625. Min Act: -0.0000

Data Index: 998847 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.0321. Min Act: -0.0000

Data Index: 633490 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 1.6973. Min Range: -1.6973

Max Act: 0.8519. Min Act: -0.0000

Data Index: 2721 (C4 (Web Text))

Max Activating Token Index: 160