Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 458 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0006

Data Index: 27482 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0645. Min Act: -0.0006

Data Index: 249530 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0613. Min Act: -0.0006

Data Index: 1133456 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0600. Min Act: -0.0005

Data Index: 919260 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0618. Min Act: -0.0006

Data Index: 703860 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0593. Min Act: -0.0006

Data Index: 903643 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0626. Min Act: -0.0006

Data Index: 878157 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0625. Min Act: -0.0006

Data Index: 455552 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0589. Min Act: -0.0006

Data Index: 829995 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0613. Min Act: -0.0005

Data Index: 762240 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0586. Min Act: -0.0006

Data Index: 1148832 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0569. Min Act: -0.0006

Data Index: 1112711 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0583. Min Act: -0.0006

Data Index: 1333231 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0616. Min Act: -0.0006

Data Index: 237425 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0584. Min Act: -0.0006

Data Index: 1269859 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0581. Min Act: -0.0006

Data Index: 1022445 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0559. Min Act: -0.0006

Data Index: 1074602 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0580. Min Act: -0.0006

Data Index: 956582 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0605. Min Act: -0.0006

Data Index: 673860 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0583. Min Act: -0.0005

Data Index: 374382 (C4 (Web Text))

Max Activating Token Index: 401