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

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

Neuron 2662 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3295. Min Act: -0.0001

Data Index: 254064 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3481. Min Act: -0.0001

Data Index: 961553 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3179. Min Act: -0.0001

Data Index: 1204283 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2767. Min Act: -0.0001

Data Index: 132645 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3210. Min Act: -0.0001

Data Index: 850912 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2998. Min Act: -0.0001

Data Index: 903860 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3049. Min Act: -0.0001

Data Index: 1141575 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3143. Min Act: -0.0001

Data Index: 719518 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2975. Min Act: -0.0001

Data Index: 991477 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2974. Min Act: -0.0001

Data Index: 806919 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2847. Min Act: -0.0001

Data Index: 552625 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2856. Min Act: -0.0001

Data Index: 773831 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2576. Min Act: -0.0001

Data Index: 169650 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3051. Min Act: -0.0001

Data Index: 852390 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3082. Min Act: -0.0001

Data Index: 176953 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2810. Min Act: -0.0001

Data Index: 1144440 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2788. Min Act: -0.0001

Data Index: 533946 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2646. Min Act: -0.0001

Data Index: 1015892 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2802. Min Act: -0.0001

Data Index: 169906 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2710. Min Act: -0.0001

Data Index: 806549 (C4 (Web Text))

Max Activating Token Index: 784