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

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

Neuron 2404 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.4526. Min Act: -0.0001

Data Index: 342310 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.4482. Min Act: -0.0001

Data Index: 190249 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.4048. Min Act: -0.0001

Data Index: 333646 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.4104. Min Act: -0.0001

Data Index: 1332592 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.4071. Min Act: -0.0001

Data Index: 932837 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3928. Min Act: -0.0001

Data Index: 136982 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3993. Min Act: -0.0001

Data Index: 583749 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3868. Min Act: -0.0001

Data Index: 381580 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3864. Min Act: -0.0001

Data Index: 636941 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3802. Min Act: -0.0001

Data Index: 362217 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3791. Min Act: -0.0001

Data Index: 302764 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3758. Min Act: -0.0001

Data Index: 320302 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3845. Min Act: -0.0001

Data Index: 489115 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3762. Min Act: -0.0001

Data Index: 1091595 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3732. Min Act: -0.0001

Data Index: 534112 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3753. Min Act: -0.0001

Data Index: 857689 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1284055 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3625. Min Act: -0.0001

Data Index: 1095837 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3653. Min Act: -0.0001

Data Index: 168029 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3568. Min Act: -0.0001

Data Index: 462680 (C4 (Web Text))

Max Activating Token Index: 978