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

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

Neuron 3896 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1237309 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.3668. Min Act: -0.0001

Data Index: 1242413 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.3307. Min Act: -0.0000

Data Index: 374534 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.3109. Min Act: -0.0001

Data Index: 141482 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.3075. Min Act: -0.0000

Data Index: 229356 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.3055. Min Act: -0.0000

Data Index: 726988 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.3047. Min Act: -0.0000

Data Index: 9562 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1032556 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2946. Min Act: -0.0001

Data Index: 90079 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2922. Min Act: -0.0001

Data Index: 1187930 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2928. Min Act: 0.0000

Data Index: 804905 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2858. Min Act: -0.0001

Data Index: 1320131 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2925. Min Act: -0.0000

Data Index: 126184 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2840. Min Act: -0.0000

Data Index: 854391 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2585. Min Act: -0.0000

Data Index: 46194 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2673. Min Act: -0.0000

Data Index: 233201 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2736. Min Act: 0.0000

Data Index: 76521 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1249820 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1232492 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2732. Min Act: -0.0001

Data Index: 399703 (C4 (Web Text))

Max Activating Token Index: 797