Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 212 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.3330. Min Act: -0.0000

Data Index: 1304114 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 3.3775. Min Range: -3.3775

Max Act: 2.6540. Min Act: -0.0000

Data Index: 96133 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2504. Min Act: -0.0000

Data Index: 775647 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1673. Min Act: -0.0000

Data Index: 1233948 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2964. Min Act: -0.0000

Data Index: 169662 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2886. Min Act: -0.0000

Data Index: 237332 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.0913. Min Act: -0.0000

Data Index: 1081712 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.3775. Min Act: -0.0000

Data Index: 1351506 (The Pile)

Max Activating Token Index: 546

Text #8

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2287. Min Act: -0.0000

Data Index: 99708 (The Pile)

Max Activating Token Index: 956

Text #9

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1804. Min Act: -0.0000

Data Index: 800411 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 3.3775. Min Range: -3.3775

Max Act: 2.7084. Min Act: -0.0000

Data Index: 393078 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 3.3775. Min Range: -3.3775

Max Act: 2.8765. Min Act: -0.0000

Data Index: 1069288 (The Pile)

Max Activating Token Index: 352

Text #12

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.0814. Min Act: -0.0000

Data Index: 668114 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 3.3775. Min Range: -3.3775

Max Act: 2.8875. Min Act: -0.0000

Data Index: 236895 (The Pile)

Max Activating Token Index: 729

Text #14

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.0617. Min Act: -0.0000

Data Index: 1152934 (The Pile)

Max Activating Token Index: 746

Text #15

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2118. Min Act: -0.0000

Data Index: 1638013 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.0391. Min Act: -0.0000

Data Index: 812708 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 3.3775. Min Range: -3.3775

Max Act: 2.5700. Min Act: -0.0000

Data Index: 1147636 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 3.3775. Min Range: -3.3775

Max Act: 2.8664. Min Act: -0.0000

Data Index: 1569155 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 3.3775. Min Range: -3.3775

Max Act: 2.1663. Min Act: -0.0000

Data Index: 1245512 (The Pile)

Max Activating Token Index: 68