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

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

Neuron 2839 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: 0.0779. Min Range: -0.0779

Max Act: 0.0747. Min Act: -0.0001

Data Index: 967244 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1172624 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0699. Min Act: -0.0001

Data Index: 375963 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1009292 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0672. Min Act: -0.0001

Data Index: 842086 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0610. Min Act: -0.0001

Data Index: 81519 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1002924 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0607. Min Act: -0.0001

Data Index: 89725 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1171778 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0589. Min Act: -0.0001

Data Index: 475818 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0609. Min Act: -0.0001

Data Index: 292514 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1222101 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0586. Min Act: -0.0001

Data Index: 977448 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0592. Min Act: -0.0001

Data Index: 270055 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0591. Min Act: -0.0001

Data Index: 845327 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0571. Min Act: -0.0001

Data Index: 626598 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0600. Min Act: -0.0001

Data Index: 616043 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0566. Min Act: -0.0001

Data Index: 182809 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0585. Min Act: -0.0001

Data Index: 677699 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0561. Min Act: -0.0000

Data Index: 112414 (C4 (Web Text))

Max Activating Token Index: 572