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

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

Neuron 1039 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: 0.2127. Min Range: -0.2127

Max Act: 0.2127. Min Act: -0.0001

Data Index: 974824 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2014. Min Act: -0.0001

Data Index: 554092 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1709. Min Act: -0.0001

Data Index: 836649 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1908. Min Act: -0.0001

Data Index: 863412 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1952. Min Act: -0.0001

Data Index: 803688 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1777. Min Act: -0.0001

Data Index: 825835 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1897. Min Act: -0.0001

Data Index: 443689 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1781. Min Act: -0.0001

Data Index: 5518 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1834. Min Act: -0.0001

Data Index: 432572 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1951. Min Act: -0.0001

Data Index: 55109 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1046281 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1612. Min Act: -0.0001

Data Index: 813957 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1663. Min Act: -0.0001

Data Index: 126865 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1632. Min Act: -0.0001

Data Index: 563996 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1749. Min Act: -0.0001

Data Index: 955539 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1209513 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1631. Min Act: -0.0001

Data Index: 224240 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1588. Min Act: -0.0001

Data Index: 152166 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1523. Min Act: -0.0001

Data Index: 953513 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1679. Min Act: -0.0001

Data Index: 411290 (C4 (Web Text))

Max Activating Token Index: 669