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

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

Neuron 4448 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1084399 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.0721. Min Act: -0.0000

Data Index: 586157 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 1.3209. Min Range: -1.3209

Max Act: 1.0163. Min Act: -0.0000

Data Index: 609135 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.7325. Min Act: -0.0000

Data Index: 233632 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.7436. Min Act: -0.0000

Data Index: 159929 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.7793. Min Act: -0.0000

Data Index: 161168 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1212609 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1155578 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.7229. Min Act: -0.0000

Data Index: 1152153 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.7781. Min Act: -0.0000

Data Index: 1119376 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.7642. Min Act: -0.0000

Data Index: 98507 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.7015. Min Act: -0.0000

Data Index: 696891 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.6924. Min Act: -0.0000

Data Index: 505611 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1035519 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.6114. Min Act: -0.0000

Data Index: 773325 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.6274. Min Act: -0.0000

Data Index: 232748 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.5769. Min Act: -0.0000

Data Index: 382735 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.5998. Min Act: -0.0000

Data Index: 891729 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1250409 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 1.3209. Min Range: -1.3209

Max Act: 0.6647. Min Act: -0.0000

Data Index: 896321 (C4 (Web Text))

Max Activating Token Index: 945