Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1355. Min Act: -0.0001

Data Index: 428903 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1129943 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1081. Min Act: -0.0001

Data Index: 931181 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1101. Min Act: -0.0001

Data Index: 558135 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1016. Min Act: -0.0001

Data Index: 205658 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0961. Min Act: -0.0001

Data Index: 228506 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0919. Min Act: -0.0001

Data Index: 948455 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0907. Min Act: -0.0001

Data Index: 177355 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0931. Min Act: -0.0001

Data Index: 856134 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0928. Min Act: -0.0001

Data Index: 72726 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0896. Min Act: -0.0000

Data Index: 877491 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0922. Min Act: -0.0001

Data Index: 378307 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0925. Min Act: -0.0001

Data Index: 481439 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1101837 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0915. Min Act: -0.0000

Data Index: 467633 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0893. Min Act: -0.0001

Data Index: 339782 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1074636 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0836. Min Act: -0.0001

Data Index: 215743 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0889. Min Act: -0.0001

Data Index: 896417 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0885. Min Act: -0.0001

Data Index: 217689 (C4 (Web Text))

Max Activating Token Index: 832