Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 97 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0001

Data Index: 350774 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0727. Min Act: -0.0001

Data Index: 604087 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0672. Min Act: -0.0001

Data Index: 603113 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0675. Min Act: -0.0001

Data Index: 108164 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0644. Min Act: -0.0001

Data Index: 262213 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0650. Min Act: -0.0001

Data Index: 13573 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0600. Min Act: -0.0000

Data Index: 39983 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1155644 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0536. Min Act: -0.0001

Data Index: 153164 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0597. Min Act: -0.0001

Data Index: 732522 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0559. Min Act: -0.0001

Data Index: 997872 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1060899 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0551. Min Act: -0.0001

Data Index: 181726 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1077166 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1353711 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1187510 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1225192 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0533. Min Act: -0.0001

Data Index: 954868 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0535. Min Act: -0.0001

Data Index: 110222 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0505. Min Act: -0.0001

Data Index: 88075 (C4 (Web Text))

Max Activating Token Index: 628