Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1157 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1916. Min Act: -0.0005

Data Index: 448417 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1817. Min Act: -0.0005

Data Index: 287071 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1750. Min Act: -0.0005

Data Index: 927883 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1705. Min Act: -0.0005

Data Index: 247623 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1710. Min Act: -0.0005

Data Index: 826594 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1659. Min Act: -0.0005

Data Index: 667247 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1669. Min Act: -0.0005

Data Index: 525275 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1639. Min Act: -0.0005

Data Index: 682259 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1680. Min Act: -0.0005

Data Index: 475428 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1682. Min Act: -0.0005

Data Index: 1024282 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1589. Min Act: -0.0005

Data Index: 754479 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1617. Min Act: -0.0005

Data Index: 797004 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1599. Min Act: -0.0005

Data Index: 940639 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1596. Min Act: -0.0005

Data Index: 1120747 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1555. Min Act: -0.0005

Data Index: 270049 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1620. Min Act: -0.0005

Data Index: 890592 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1529. Min Act: -0.0005

Data Index: 624642 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1531. Min Act: -0.0005

Data Index: 654432 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1576. Min Act: -0.0005

Data Index: 1036791 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1451. Min Act: -0.0005

Data Index: 45694 (C4 (Web Text))

Max Activating Token Index: 1015