Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2793 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1282029 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1917. Min Act: -0.0001

Data Index: 546740 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2060. Min Act: -0.0001

Data Index: 1141423 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2021. Min Act: -0.0001

Data Index: 250059 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1972. Min Act: -0.0001

Data Index: 317360 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1752. Min Act: -0.0001

Data Index: 258661 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1021933 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1621. Min Act: -0.0001

Data Index: 216514 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1871. Min Act: -0.0001

Data Index: 159741 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1900. Min Act: -0.0001

Data Index: 681781 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1836. Min Act: -0.0001

Data Index: 780427 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1757. Min Act: -0.0001

Data Index: 75047 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1441801 (Python Code)

Max Activating Token Index: 854

Text #13

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1852. Min Act: -0.0001

Data Index: 1349695 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1565. Min Act: -0.0001

Data Index: 995335 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1718. Min Act: -0.0001

Data Index: 528921 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1771. Min Act: -0.0001

Data Index: 37072 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1553. Min Act: -0.0001

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1850. Min Act: -0.0001

Data Index: 277995 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1169763 (C4 (Web Text))

Max Activating Token Index: 108