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

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

Neuron 2160 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5311. Min Act: -0.0000

Data Index: 509041 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.7232. Min Act: -0.0000

Data Index: 410123 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.7039. Min Act: -0.0000

Data Index: 691240 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.7607. Min Act: -0.0000

Data Index: 1210330 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.3192. Min Act: -0.0000

Data Index: 187397 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.3730. Min Act: -0.0000

Data Index: 640690 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.2124. Min Act: -0.0000

Data Index: 670495 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.3939. Min Act: -0.0000

Data Index: 394365 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.4847. Min Act: -0.0000

Data Index: 160413 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.3904. Min Act: -0.0000

Data Index: 7677 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.2255. Min Act: -0.0000

Data Index: 499872 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1228339 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.1116. Min Act: -0.0000

Data Index: 671236 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 1.7607. Min Range: -1.7607

Max Act: 0.9329. Min Act: -0.0000

Data Index: 657947 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.4021. Min Act: -0.0000

Data Index: 119788 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.1553. Min Act: -0.0000

Data Index: 807471 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.2873. Min Act: -0.0000

Data Index: 751609 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1179036 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.1205. Min Act: -0.0000

Data Index: 965558 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.2592. Min Act: -0.0000

Data Index: 979701 (C4 (Web Text))

Max Activating Token Index: 980