Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1860 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1241062 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5958. Min Act: -0.0000

Data Index: 822375 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5392. Min Act: -0.0000

Data Index: 972685 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5069. Min Act: -0.0000

Data Index: 878481 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5099. Min Act: -0.0000

Data Index: 60920 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4931. Min Act: -0.0000

Data Index: 998606 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4974. Min Act: -0.0000

Data Index: 734826 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1073641 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5058. Min Act: -0.0000

Data Index: 150888 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4937. Min Act: -0.0000

Data Index: 350248 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4780. Min Act: -0.0000

Data Index: 683022 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1248856 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4755. Min Act: -0.0000

Data Index: 349485 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4597. Min Act: -0.0000

Data Index: 650587 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4553. Min Act: -0.0000

Data Index: 372175 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4520. Min Act: -0.0000

Data Index: 444659 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4551. Min Act: 0.0000

Data Index: 609342 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1305593 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4519. Min Act: -0.0000

Data Index: 622477 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4391. Min Act: 0.0000

Data Index: 55092 (C4 (Web Text))

Max Activating Token Index: 231