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

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

Neuron 1506 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4988. Min Range: -3.4988

Max Act: 3.4988. Min Act: -0.0000

Data Index: 366986 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 3.4988. Min Range: -3.4988

Max Act: 2.8411. Min Act: -0.0000

Data Index: 991550 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 3.4988. Min Range: -3.4988

Max Act: 2.7926. Min Act: -0.0000

Data Index: 33300 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 3.4988. Min Range: -3.4988

Max Act: 2.3808. Min Act: -0.0000

Data Index: 985558 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 3.4988. Min Range: -3.4988

Max Act: 2.3106. Min Act: -0.0000

Data Index: 760342 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.9742. Min Act: -0.0000

Data Index: 1132728 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 3.4988. Min Range: -3.4988

Max Act: 2.0027. Min Act: -0.0000

Data Index: 353108 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.9749. Min Act: -0.0000

Data Index: 400798 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.9693. Min Act: -0.0000

Data Index: 1183638 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.9231. Min Act: -0.0000

Data Index: 716426 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.9386. Min Act: -0.0000

Data Index: 325626 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.7177. Min Act: -0.0000

Data Index: 1356181 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.8157. Min Act: -0.0000

Data Index: 1263289 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.9048. Min Act: -0.0000

Data Index: 1157951 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.7653. Min Act: -0.0000

Data Index: 292527 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.8811. Min Act: -0.0000

Data Index: 121568 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.6401. Min Act: -0.0000

Data Index: 1056113 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.7776. Min Act: -0.0000

Data Index: 510340 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.6676. Min Act: -0.0000

Data Index: 547447 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 3.4988. Min Range: -3.4988

Max Act: 1.8151. Min Act: -0.0000

Data Index: 35171 (C4 (Web Text))

Max Activating Token Index: 711