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

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

Neuron 1879 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1100. Min Range: -2.1100

Max Act: 2.1100. Min Act: -0.0001

Data Index: 1062855 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.1100. Min Range: -2.1100

Max Act: 2.0435. Min Act: -0.0001

Data Index: 136758 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.7111. Min Act: -0.0001

Data Index: 32442 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.8079. Min Act: -0.0001

Data Index: 128501 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.6813. Min Act: -0.0001

Data Index: 600344 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.6608. Min Act: -0.0001

Data Index: 94355 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5700. Min Act: -0.0001

Data Index: 1055420 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5541. Min Act: -0.0001

Data Index: 1074981 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5823. Min Act: -0.0001

Data Index: 644743 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5817. Min Act: -0.0001

Data Index: 747909 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5705. Min Act: -0.0001

Data Index: 870269 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5294. Min Act: -0.0001

Data Index: 491059 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5634. Min Act: -0.0001

Data Index: 1063909 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.4546. Min Act: -0.0001

Data Index: 1191343 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5032. Min Act: -0.0001

Data Index: 335109 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.4820. Min Act: -0.0001

Data Index: 694276 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.4803. Min Act: -0.0001

Data Index: 281606 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5108. Min Act: -0.0001

Data Index: 1473896 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.4040. Min Act: -0.0001

Data Index: 482747 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.4806. Min Act: -0.0001

Data Index: 615745 (C4 (Web Text))

Max Activating Token Index: 741