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

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

Neuron 4137 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4930. Min Range: -4.4930

Max Act: 4.4930. Min Act: -0.0000

Data Index: 656076 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 4.4930. Min Range: -4.4930

Max Act: 4.1437. Min Act: -0.0000

Data Index: 91739 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.8707. Min Act: -0.0000

Data Index: 933568 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 4.4930. Min Range: -4.4930

Max Act: 4.0008. Min Act: -0.0000

Data Index: 675587 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.6822. Min Act: -0.0000

Data Index: 493007 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.5036. Min Act: -0.0000

Data Index: 543884 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.5094. Min Act: -0.0000

Data Index: 153433 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.2859. Min Act: -0.0000

Data Index: 873658 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.2615. Min Act: -0.0000

Data Index: 187513 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.3586. Min Act: -0.0000

Data Index: 986998 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.4746. Min Act: -0.0000

Data Index: 259988 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.1630. Min Act: -0.0000

Data Index: 473479 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.4417. Min Act: -0.0000

Data Index: 799930 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.4352. Min Act: -0.0000

Data Index: 785797 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.2150. Min Act: -0.0000

Data Index: 152124 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 4.4930. Min Range: -4.4930

Max Act: 2.8223. Min Act: -0.0000

Data Index: 362735 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.2559. Min Act: -0.0000

Data Index: 148245 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.0412. Min Act: -0.0000

Data Index: 1069223 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.2022. Min Act: -0.0000

Data Index: 138418 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 4.4930. Min Range: -4.4930

Max Act: 3.0760. Min Act: -0.0000

Data Index: 793551 (C4 (Web Text))

Max Activating Token Index: 563