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

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

Neuron 1452 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3609. Min Act: -0.0001

Data Index: 141509 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3676. Min Act: -0.0001

Data Index: 601599 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3234. Min Act: -0.0001

Data Index: 449127 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3361. Min Act: -0.0001

Data Index: 301732 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3006. Min Act: -0.0001

Data Index: 604295 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3022. Min Act: -0.0001

Data Index: 475964 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3062. Min Act: -0.0001

Data Index: 669747 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2856. Min Act: -0.0001

Data Index: 14095 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2862. Min Act: -0.0001

Data Index: 1081357 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2821. Min Act: -0.0001

Data Index: 470176 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2800. Min Act: -0.0001

Data Index: 251943 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2836. Min Act: -0.0001

Data Index: 670174 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2758. Min Act: -0.0001

Data Index: 1123587 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2715. Min Act: -0.0001

Data Index: 396199 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2763. Min Act: -0.0001

Data Index: 975944 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2783. Min Act: -0.0001

Data Index: 555363 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2960. Min Act: -0.0001

Data Index: 1230897 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2858. Min Act: -0.0001

Data Index: 465223 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2637. Min Act: -0.0001

Data Index: 1181062 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2703. Min Act: -0.0001

Data Index: 260656 (C4 (Web Text))

Max Activating Token Index: 182