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

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

Neuron 1612 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.2150. Min Act: -0.0001

Data Index: 1051244 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.2869. Min Act: -0.0001

Data Index: 14632 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.2847. Min Act: -0.0001

Data Index: 1232512 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.2220. Min Act: -0.0001

Data Index: 105818 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.2476. Min Act: -0.0001

Data Index: 700070 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.0937. Min Act: -0.0001

Data Index: 260815 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.2086. Min Act: -0.0001

Data Index: 23762 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.1037. Min Act: -0.0001

Data Index: 701728 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.0116. Min Act: -0.0001

Data Index: 810154 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.0709. Min Act: -0.0001

Data Index: 1149402 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.0531. Min Act: -0.0001

Data Index: 1284910 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.2869. Min Range: -1.2869

Max Act: 1.0362. Min Act: -0.0001

Data Index: 62508 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 1.2869. Min Range: -1.2869

Max Act: 0.9656. Min Act: -0.0001

Data Index: 689110 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.2869. Min Range: -1.2869

Max Act: 0.9688. Min Act: -0.0001

Data Index: 543587 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.2869. Min Range: -1.2869

Max Act: 0.9667. Min Act: -0.0001

Data Index: 162857 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.2869. Min Range: -1.2869

Max Act: 0.9320. Min Act: -0.0001

Data Index: 39222 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 1.2869. Min Range: -1.2869

Max Act: 0.8848. Min Act: -0.0001

Data Index: 1007736 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.2869. Min Range: -1.2869

Max Act: 0.9072. Min Act: -0.0001

Data Index: 1142792 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.2869. Min Range: -1.2869

Max Act: 0.9287. Min Act: -0.0001

Data Index: 1021181 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 1.2869. Min Range: -1.2869

Max Act: 0.8706. Min Act: -0.0001

Data Index: 946860 (C4 (Web Text))

Max Activating Token Index: 222