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

Dataset: The Pile

Neuron 1432 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1985822 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9684. Min Act: -0.0000

Data Index: 1087148 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0442. Min Act: -0.0000

Data Index: 62361 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1864390 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9703. Min Act: -0.0000

Data Index: 95804 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1640592 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1691242 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9703. Min Act: -0.0000

Data Index: 196659 (The Pile)

Max Activating Token Index: 75

Text #8

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1081645 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9272. Min Act: -0.0000

Data Index: 366138 (The Pile)

Max Activating Token Index: 93

Text #10

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1788367 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1621190 (The Pile)

Max Activating Token Index: 909

Text #12

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1630349 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1207886 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8608. Min Act: -0.0000

Data Index: 849421 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1439001 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1378742 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8980. Min Act: -0.0000

Data Index: 164466 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1920920 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1677134 (The Pile)

Max Activating Token Index: 200