Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3096 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2730. Min Act: -0.0001

Data Index: 740263 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2282. Min Act: -0.0001

Data Index: 1067141 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2175. Min Act: -0.0001

Data Index: 804185 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1313960 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1305215 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2082. Min Act: -0.0001

Data Index: 810647 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1241624 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2092. Min Act: -0.0001

Data Index: 1037846 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2033. Min Act: -0.0001

Data Index: 294152 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2065. Min Act: -0.0001

Data Index: 733304 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1314873 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2036. Min Act: -0.0001

Data Index: 679683 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1164698 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.2061. Min Act: -0.0001

Data Index: 455391 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.1990. Min Act: -0.0001

Data Index: 70513 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.1986. Min Act: -0.0001

Data Index: 878888 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.1940. Min Act: -0.0001

Data Index: 184951 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1103980 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.1909. Min Act: -0.0001

Data Index: 323938 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.2730. Min Range: -0.2730

Max Act: 0.1912. Min Act: -0.0001

Data Index: 1070073 (C4 (Web Text))

Max Activating Token Index: 56