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

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

Neuron 2654 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: 2.1644. Min Range: -2.1644

Max Act: 2.1644. Min Act: -0.0000

Data Index: 222319 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.4093. Min Act: -0.0000

Data Index: 814643 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.2612. Min Act: -0.0000

Data Index: 782957 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.3273. Min Act: 0.0000

Data Index: 221289 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.2344. Min Act: 0.0001

Data Index: 1200778 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.3133. Min Act: 0.0001

Data Index: 1255293 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.3023. Min Act: -0.0000

Data Index: 465799 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.2825. Min Act: -0.0000

Data Index: 221899 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.2537. Min Act: -0.0000

Data Index: 775067 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.2349. Min Act: 0.0001

Data Index: 523839 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.2104. Min Act: -0.0000

Data Index: 401131 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1111067 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.1856. Min Act: 0.0000

Data Index: 1239746 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.1765. Min Act: -0.0000

Data Index: 843346 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.1504. Min Act: -0.0000

Data Index: 653181 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1091117 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.0499. Min Act: -0.0000

Data Index: 434040 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.1873. Min Act: 0.0001

Data Index: 86545 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 2.1644. Min Range: -2.1644

Max Act: 1.1823. Min Act: -0.0000

Data Index: 1238456 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 2.1644. Min Range: -2.1644

Max Act: 0.9932. Min Act: -0.0000

Data Index: 891498 (C4 (Web Text))

Max Activating Token Index: 911