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

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

Neuron 3857 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8474. Min Act: -0.0001

Data Index: 403515 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8227. Min Act: -0.0001

Data Index: 642595 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8124. Min Act: -0.0001

Data Index: 518759 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8266. Min Act: -0.0001

Data Index: 1067596 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7772. Min Act: -0.0001

Data Index: 547661 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7783. Min Act: -0.0001

Data Index: 776876 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7537. Min Act: -0.0001

Data Index: 1167919 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7384. Min Act: -0.0001

Data Index: 904289 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1133814 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1087334 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7024. Min Act: -0.0001

Data Index: 39107 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6779. Min Act: -0.0000

Data Index: 319736 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6949. Min Act: -0.0000

Data Index: 603270 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6674. Min Act: -0.0001

Data Index: 1036669 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8007. Min Act: -0.0001

Data Index: 565594 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6957. Min Act: -0.0001

Data Index: 135616 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6536. Min Act: -0.0001

Data Index: 544061 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7112. Min Act: -0.0001

Data Index: 843114 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6484. Min Act: -0.0001

Data Index: 891991 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6629. Min Act: -0.0001

Data Index: 1016304 (C4 (Web Text))

Max Activating Token Index: 334