Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2092 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1143590 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1816. Min Act: -0.0001

Data Index: 578399 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.2089. Min Act: -0.0001

Data Index: 896337 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1924. Min Act: -0.0001

Data Index: 639785 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1803. Min Act: -0.0001

Data Index: 343070 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1895. Min Act: -0.0001

Data Index: 896841 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1814. Min Act: -0.0001

Data Index: 753495 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1619. Min Act: -0.0001

Data Index: 271013 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1680. Min Act: -0.0001

Data Index: 906941 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1358318 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1712. Min Act: -0.0001

Data Index: 945518 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1332132 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1669. Min Act: -0.0001

Data Index: 374435 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1644. Min Act: -0.0001

Data Index: 993454 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1287618 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1248274 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1539. Min Act: -0.0001

Data Index: 927438 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1563. Min Act: -0.0001

Data Index: 389238 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1153096 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1554. Min Act: -0.0001

Data Index: 80330 (C4 (Web Text))

Max Activating Token Index: 703