Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2985 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0001

Data Index: 161657 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0554. Min Act: -0.0001

Data Index: 112015 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0568. Min Act: -0.0001

Data Index: 371156 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0545. Min Act: -0.0001

Data Index: 350041 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1183349 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0581. Min Act: -0.0001

Data Index: 272038 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1150642 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1353855 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0551. Min Act: -0.0001

Data Index: 62135 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0531. Min Act: -0.0001

Data Index: 509041 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0516. Min Act: -0.0002

Data Index: 848299 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0549. Min Act: -0.0001

Data Index: 545322 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0543. Min Act: -0.0001

Data Index: 481939 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0527. Min Act: -0.0001

Data Index: 775784 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0535. Min Act: -0.0001

Data Index: 167072 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0582. Min Act: -0.0001

Data Index: 463579 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0498. Min Act: -0.0002

Data Index: 279865 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1078407 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0520. Min Act: -0.0002

Data Index: 474219 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0442. Min Act: -0.0001

Data Index: 200136 (C4 (Web Text))

Max Activating Token Index: 590