Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1439 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.1035. Min Act: -0.0003

Data Index: 639779 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.1026. Min Act: -0.0003

Data Index: 478693 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0974. Min Act: -0.0003

Data Index: 169280 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0989. Min Act: -0.0003

Data Index: 1021472 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0950. Min Act: -0.0003

Data Index: 340194 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0947. Min Act: -0.0003

Data Index: 210805 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0948. Min Act: -0.0004

Data Index: 648746 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0942. Min Act: -0.0003

Data Index: 832549 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0937. Min Act: -0.0003

Data Index: 874229 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0936. Min Act: -0.0003

Data Index: 980048 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0918. Min Act: -0.0003

Data Index: 556275 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0935. Min Act: -0.0003

Data Index: 60114 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0962. Min Act: -0.0003

Data Index: 1068658 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0904. Min Act: -0.0003

Data Index: 452240 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0888. Min Act: -0.0004

Data Index: 1085750 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1123433 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0915. Min Act: -0.0003

Data Index: 864264 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0869. Min Act: -0.0003

Data Index: 308895 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0868. Min Act: -0.0003

Data Index: 1292474 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0860. Min Act: -0.0003

Data Index: 161392 (C4 (Web Text))

Max Activating Token Index: 210