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

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

Neuron 2360 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: 2.8207. Min Range: -2.8207

Max Act: 2.8207. Min Act: -0.0000

Data Index: 1218941 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 2.8207. Min Range: -2.8207

Max Act: 2.2913. Min Act: -0.0000

Data Index: 249641 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 2.8207. Min Range: -2.8207

Max Act: 2.4379. Min Act: -0.0000

Data Index: 705388 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 2.8207. Min Range: -2.8207

Max Act: 2.2804. Min Act: -0.0000

Data Index: 603096 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 2.8207. Min Range: -2.8207

Max Act: 2.0130. Min Act: -0.0000

Data Index: 810400 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.9127. Min Act: -0.0000

Data Index: 595418 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.8994. Min Act: -0.0000

Data Index: 39438 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.9667. Min Act: -0.0000

Data Index: 684703 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.9252. Min Act: -0.0000

Data Index: 979248 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.7810. Min Act: -0.0000

Data Index: 254960 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.7794. Min Act: -0.0000

Data Index: 667799 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.5428. Min Act: -0.0000

Data Index: 727008 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.7316. Min Act: -0.0000

Data Index: 327847 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.6699. Min Act: -0.0000

Data Index: 194176 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.5797. Min Act: -0.0000

Data Index: 1240961 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1062417 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.6031. Min Act: -0.0000

Data Index: 464938 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.3636. Min Act: -0.0000

Data Index: 1087963 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.3802. Min Act: -0.0000

Data Index: 804895 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 2.8207. Min Range: -2.8207

Max Act: 1.4515. Min Act: -0.0000

Data Index: 698162 (C4 (Web Text))

Max Activating Token Index: 379