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

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

Neuron 5350 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1198577 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1091. Min Act: -0.0001

Data Index: 978820 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1005. Min Act: -0.0001

Data Index: 900631 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1006. Min Act: -0.0001

Data Index: 809138 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1061. Min Act: -0.0001

Data Index: 671313 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1014. Min Act: -0.0001

Data Index: 979020 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1278934 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1012. Min Act: -0.0001

Data Index: 688231 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0923. Min Act: -0.0001

Data Index: 586961 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0868. Min Act: -0.0001

Data Index: 12776 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0847. Min Act: -0.0002

Data Index: 797834 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0914. Min Act: -0.0001

Data Index: 795995 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0970. Min Act: -0.0002

Data Index: 98901 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0890. Min Act: -0.0001

Data Index: 56887 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0912. Min Act: -0.0001

Data Index: 575338 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0911. Min Act: -0.0001

Data Index: 524725 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1183574 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0862. Min Act: -0.0001

Data Index: 201606 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0915. Min Act: -0.0001

Data Index: 388439 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0900. Min Act: -0.0001

Data Index: 964527 (C4 (Web Text))

Max Activating Token Index: 84