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

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

Neuron 565 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1874. Min Act: -0.0001

Data Index: 560088 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1931. Min Act: -0.0001

Data Index: 817237 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1775. Min Act: -0.0001

Data Index: 1075154 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1830. Min Act: -0.0001

Data Index: 756158 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1111610 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1723. Min Act: -0.0001

Data Index: 675356 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1658. Min Act: -0.0001

Data Index: 30831 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1092486 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1611. Min Act: -0.0001

Data Index: 354347 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1038319 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1525. Min Act: -0.0001

Data Index: 875238 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1592. Min Act: -0.0001

Data Index: 411733 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1646. Min Act: -0.0001

Data Index: 181609 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1723. Min Act: -0.0001

Data Index: 622053 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1615. Min Act: -0.0001

Data Index: 1097196 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1541. Min Act: -0.0001

Data Index: 275426 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1496. Min Act: -0.0001

Data Index: 544404 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1191582 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1530. Min Act: -0.0001

Data Index: 835800 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1466. Min Act: -0.0001

Data Index: 659717 (C4 (Web Text))

Max Activating Token Index: 439