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

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

Neuron 2427 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: 0.0666. Min Range: -0.0666

Max Act: 0.0642. Min Act: -0.0002

Data Index: 300432 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0002

Data Index: 972800 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1109740 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0659. Min Act: -0.0002

Data Index: 68472 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0660. Min Act: -0.0001

Data Index: 911865 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1097182 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0594. Min Act: -0.0002

Data Index: 850324 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0580. Min Act: -0.0002

Data Index: 429929 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0593. Min Act: -0.0002

Data Index: 19739 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0570. Min Act: -0.0001

Data Index: 589829 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1090649 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1340579 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1170068 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0585. Min Act: -0.0002

Data Index: 377188 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0506. Min Act: -0.0002

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0514. Min Act: -0.0002

Data Index: 502402 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0573. Min Act: -0.0002

Data Index: 968625 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0530. Min Act: -0.0002

Data Index: 61010 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1071448 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0573. Min Act: -0.0002

Data Index: 892305 (C4 (Web Text))

Max Activating Token Index: 994